Search Results for author:
Found 151 papers, 28 papers with code
Semantically Controllable Augmentations for Generalizable Robot Learning
By demonstrating the effectiveness of image-text generative models in diverse real-world robotic applications, our generative augmentation framework provides a scalable and efficient path for boosting generalization in robot learning at no extra human cost.
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences.
Improving Self-supervised Pre-training using Accent-Specific Codebooks
Speech accents present a serious challenge to the performance of state-of-the-art end-to-end Automatic Speech Recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images
We present an integrated end-to-end pipeline that generates simulation scenes complete with articulated kinematic and dynamic structures from real-world images and use these for training robotic control policies.
Parameter Identification for Electrochemical Models of Lithium-Ion Batteries Using Bayesian Optimization
Efficient parameter identification of electrochemical models is crucial for accurate monitoring and control of lithium-ion cells.
Bridging the Gap Between Theory and Practice: Benchmarking Transfer Evolutionary Optimization
This paper pioneers a practical TrEO benchmark suite, integrating problems from the literature categorized based on the three essential aspects of Big Source Task-Instances: volume, variety, and velocity.
ASID: Active Exploration for System Identification in Robotic Manipulation
In this work, we propose a learning system that can leverage a small amount of real-world data to autonomously refine a simulation model and then plan an accurate control strategy that can be deployed in the real world.
Multi-Task Learning with Multi-Task Optimization
Multi-task learning solves multiple correlated tasks.
Transferable Reinforcement Learning via Generalized Occupancy Models
This work proposes a novel class of models, i. e., generalized occupancy models (GOMs), that learn a distribution of successor features from a stationary dataset, along with a policy that acts to realize different successor features.
Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
To learn performant, robust policies without the burden of unsafe real-world data collection or extensive human supervision, we propose RialTo, a system for robustifying real-world imitation learning policies via reinforcement learning in "digital twin" simulation environments constructed on the fly from small amounts of real-world data.
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
We posit that a significant challenge to widespread adoption of robotic RL, as well as further development of robotic RL methods, is the comparative inaccessibility of such methods.
Multiform Evolution for High-Dimensional Problems with Low Effective Dimensionality
In this paper, we scale evolutionary algorithms to high-dimensional optimization problems that deceptively possess a low effective dimensionality (certain dimensions do not significantly affect the objective function).
Bayesian Inverse Transfer in Evolutionary Multiobjective Optimization
In this paper, we introduce a novel concept of \textit{inverse transfer} in multiobjective optimization.
Model-Free Change Point Detection for Mixing Processes
In particular, we provide performance guarantees for the MMD-CUSUM test under exponentially $\alpha$, $\beta$, and fast $\phi$-mixing processes, which significantly expands its utility beyond the i. i. d.
Modeling Boundedly Rational Agents with Latent Inference Budgets
We study the problem of modeling a population of agents pursuing unknown goals subject to unknown computational constraints.
Generalizable Neural Physics Solvers by Baldwinian Evolution
Physics-informed neural networks (PINNs) are at the forefront of scientific machine learning, making possible the creation of machine intelligence that is cognizant of physical laws and able to accurately simulate them.
New Epochs in AI Supervision: Design and Implementation of an Autonomous Radiology AI Monitoring System
With the increasingly widespread adoption of AI in healthcare, maintaining the accuracy and reliability of AI models in clinical practice has become crucial.
Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback
We evaluate this system on a suite of robotic tasks in simulation and demonstrate its effectiveness at learning behaviors both in simulation and the real world.
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
Off-policy dynamic programming (DP) techniques such as $Q$-learning have proven to be important in sequential decision-making problems.
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
Learning long-horizon manipulation tasks, however, is a long-standing challenge, and demands decomposing the overarching task into several manageable subtasks to facilitate policy learning and generalization to unseen tasks.
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets
We argue this is due to an assumption made by current offline RL algorithms of staying close to the trajectories in the dataset.
Hoeffding's Inequality for Markov Chains under Generalized Concentrability Condition
This paper studies Hoeffding's inequality for Markov chains under the generalized concentrability condition defined via integral probability metric (IPM).
Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives
Recent decisions by leading AI labs to either open-source their models or to restrict access to their models has sparked debate about whether, and how, increasingly capable AI models should be shared.
Lifelong Robot Learning with Human Assisted Language Planners
Large Language Models (LLMs) have been shown to act like planners that can decompose high-level instructions into a sequence of executable instructions.
REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation
We demonstrate the benefits of reusing past data as replay buffer initialization for new tasks, for instance, the fast acquisition of intricate manipulation skills in the real world on a four-fingered robotic hand.
Maximizing Success Rate of Payment Routing using Non-stationary Bandits
This paper discusses the system architecture design and deployment of non-stationary multi-armed bandit approaches to determine a near-optimal payment routing policy based on the recent history of transactions.
Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses.
Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective
Focusing on the special case where the labels are given by bilinear embeddings into a Hilbert space $H$: $\mathbb{E}[z \mid x, y ]=\langle f_{\star}(x), g_{\star}(y)\rangle_{{H}}$, we aim to extrapolate to a test distribution domain that is $not$ covered in training, i. e., achieving bilinear combinatorial extrapolation.
Cobalt: Optimizing Mining Rewards in Proof-of-Work Network Games
To maximize rewards a miner must choose its network connections carefully, ensuring existence of paths to other miners that are on average of a lower latency compared to paths between other miners.
Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching
However, in order to apply them effectively in offline optimization paradigms such as offline Reinforcement Learning (RL) or Imitation Learning (IL), we require a more careful consideration of how uncertainty estimation interplays with first-order methods that attempt to minimize them.
Navigating Fairness in Radiology AI: Concepts, Consequences,and Crucial Considerations
This review discusses the concept of fairness in AI, focusing on bias auditing using the Aequitas toolkit, and its real-world implications in radiology, particularly in disease screening scenarios.
Prompt Evolution for Generative AI: A Classifier-Guided Approach
Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI.
Learning to Extrapolate: A Transductive Approach
Machine learning systems, especially with overparameterized deep neural networks, can generalize to novel test instances drawn from the same distribution as the training data.
Asking Better Questions -- The Art and Science of Forecasting: A mechanism for truer answers to high-stakes questions
Without the ability to estimate and benchmark AI capability advancements, organizations are left to respond to each change reactively, impeding their ability to build viable mid and long-term strategies.
Augmented Collective Intelligence in Collaborative Ideation: Agenda and Challenges
AI systems may be better thought of as peers than as tools.
Deep Linear Discriminant Analysis with Variation for Polycystic Ovary Syndrome Classification
The polycystic ovary syndrome diagnosis is a problem that can be leveraged using prognostication based learning procedures.
TactoFind: A Tactile Only System for Object Retrieval
We study the problem of object retrieval in scenarios where visual sensing is absent, object shapes are unknown beforehand and objects can move freely, like grabbing objects out of a drawer.
Guiding Pretraining in Reinforcement Learning with Large Language Models
Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function.
Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance
In this paper, we describe a system for vision-based dexterous manipulation that provides a "programming-free" approach for users to define new tasks and enable robots with complex multi-fingered hands to learn to perform them through interaction.
Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and Comparative Results
Hence, neuroevolution algorithms, with their superior global search capacity, may be a better choice for PINNs relative to gradient descent methods.
Forged Image Detection using SOTA Image Classification Deep Learning Methods for Image Forensics with Error Level Analysis
Forgery of images is sub-category of image forensics and can be detected using Error Level Analysis.
Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the reward only needs to specify what the task is, in reality practitioners often need to design more detailed rewards that provide the agent with some hints about how the task should be completed.
Distributionally Adaptive Meta Reinforcement Learning
In this work, we develop a framework for meta-RL algorithms that are able to behave appropriately under test-time distribution shifts in the space of tasks.
DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations
The policy learned from our dataset can generalize well on unseen object poses in both simulation and the real world
Importance Prioritized Policy Distillation
Given such an issue, we denote the \emph{frame importance} as its contribution to the expected reward on a particular frame, and hypothesize that adapting such frame importance could benefit the performance of the distilled student policy.
Metric Effects based on Fluctuations in values of k in Nearest Neighbor Regressor
Regression branch of Machine Learning purely focuses on prediction of continuous values.
Preemptive Scheduling of EV Charging for Providing Demand Response Services
We develop a new algorithm for scheduling the charging process of a large number of electric vehicles (EVs) over a finite horizon.
Performance Comparison of Simple Transformer and Res-CNN-BiLSTM for Cyberbullying Classification
In this paper we present a performance based comparison between simple transformer based network and Res-CNN-BiLSTM based network for cyberbullying text classification problem.
Prediction of Maneuvering Status for Aerial Vehicles using Supervised Learning Methods
Aerial Vehicles follow a guided approach based on Latitude, Longitude and Altitude.
Residual-Concatenate Neural Network with Deep Regularization Layers for Binary Classification
Many complex Deep Learning models are used with different variations for various prognostication tasks.
Jack and Masters of all Trades: One-Pass Learning Sets of Model Sets From Large Pre-Trained Models
For deep learning, size is power.
Res-CNN-BiLSTM Network for overcoming Mental Health Disturbances caused due to Cyberbullying through Social Media
Mental Health Disturbance has many reasons and cyberbullying is one of the major causes that does exploitation using social media as an instrument.
Detection of Tool based Edited Images from Error Level Analysis and Convolutional Neural Network
Image Forgery is a problem of image forensics and its detection can be leveraged using Deep Learning.
Multitask Neuroevolution for Reinforcement Learning with Long and Short Episodes
This paper is the first to address the shortcoming of today's methods via a novel neuroevolutionary multitasking (NuEMT) algorithm, designed to transfer information from a set of auxiliary tasks (of short episode length) to the target (full length) RL task at hand.
Teachable Reinforcement Learning via Advice Distillation
Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infrastructure and access to a human expert, and learning from intermediate forms of supervision (like binary preferences) is time-consuming and extracts little information from each human intervention.
Combining Varied Learners for Binary Classification using Stacked Generalization
The Machine Learning has various learning algorithms that are better in some or the other aspect when compared with each other but a common error that all algorithms will suffer from is training data with very high dimensional feature set.
Binary Classification for High Dimensional Data using Supervised Non-Parametric Ensemble Method
High dimensional data for classification does create many difficulties for machine learning algorithms.
HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment
All training and testing 3D skeletons in HAA4D are globally aligned, using a deep alignment model to the same global space, making each skeleton face the negative z-direction.
State of AI Ethics Report (Volume 6, February 2022)
This report from the Montreal AI Ethics Institute (MAIEI) covers the most salient progress in research and reporting over the second half of 2021 in the field of AI ethics.
Effects of Parametric and Non-Parametric Methods on High Dimensional Sparse Matrix Representations
The semantics are derived from textual data that provide representations for Machine Learning algorithms.
Change Detection of Markov Kernels with Unknown Pre and Post Change Kernel
In this paper, we develop a new change detection algorithm for detecting a change in the Markov kernel over a metric space in which the post-change kernel is unknown.
Discriminant Analysis in Contrasting Dimensions for Polycystic Ovary Syndrome Prognostication
A lot of prognostication methodologies have been formulated for early detection of Polycystic Ovary Syndrome also known as PCOS using Machine Learning.
Succinct Differentiation of Disparate Boosting Ensemble Learning Methods for Prognostication of Polycystic Ovary Syndrome Diagnosis
Prognostication of medical problems using the clinical data by leveraging the Machine Learning techniques with stellar precision is one of the most important real world challenges at the present time.
Autonomous Reinforcement Learning: Formalism and Benchmarking
In this paper, we aim to address this discrepancy by laying out a framework for Autonomous Reinforcement Learning (ARL): reinforcement learning where the agent not only learns through its own experience, but also contends with lack of human supervision to reset between trials.
A Dynamic Watermarking Algorithm for Finite Markov Decision Problems
Dynamic watermarking, as an active intrusion detection technique, can potentially detect replay attacks, spoofing attacks, and deception attacks in the feedback channel for control systems.
Offline RL With Resource Constrained Online Deployment
We address this performance gap with a policy transfer algorithm which first trains a teacher agent using the offline dataset where features are fully available, and then transfers this knowledge to a student agent that only uses the resource-constrained features.
Offline Reinforcement Learning with Resource Constrained Online Deployment
We address this performance gap with a policy transfer algorithm which first trains a teacher agent using the offline dataset where features are fully available, and then transfers this knowledge to a student agent that only uses the resource-constrained features.
Half a Dozen Real-World Applications of Evolutionary Multitasking, and More
Until recently, the potential to transfer evolved skills across distinct optimization problem instances (or tasks) was seldom explored in evolutionary computation.
Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
In this paper, we present a novel perspective of the merits of learning in sinusoidal spaces with PINNs.
The State of AI Ethics Report (Volume 5)
This report from the Montreal AI Ethics Institute covers the most salient progress in research and reporting over the second quarter of 2021 in the field of AI ethics with a special emphasis on "Environment and AI", "Creativity and AI", and "Geopolitics and AI."
Real-time Eco-Driving Control in Electrified Connected and Autonomous Vehicles using Approximate Dynamic Programming
This paper presents a hierarchical multi-layer Model Predictive Control (MPC) approach for improving the fuel economy of a 48V mild-hybrid powertrain in a connected vehicle environment.
Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
Our aim is to devise a robotic reinforcement learning system for learning navigation and manipulation together, in an autonomous way without human intervention, enabling continual learning under realistic assumptions.
Autonomous Reinforcement Learning via Subgoal Curricula
Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents.
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
In this work, we show that an uncertainty aware classifier can solve challenging reinforcement learning problems by both encouraging exploration and provided directed guidance towards positive outcomes.
Weighted Gaussian Process Bandits for Non-stationary Environments
To this end, we develop WGP-UCB, a novel UCB-type algorithm based on weighted Gaussian process regression.
Which Mutual-Information Representation Learning Objectives are Sufficient for Control?
Mutual information maximization provides an appealing formalism for learning representations of data.
Safe Model-based Off-policy Reinforcement Learning for Eco-Driving in Connected and Automated Hybrid Electric Vehicles
Connected and Automated Hybrid Electric Vehicles have the potential to reduce fuel consumption and travel time in real-world driving conditions.
Model-based Reinforcement Learning
reinforcement-learning
+1
The State of AI Ethics Report (January 2021)
The 3rd edition of the Montreal AI Ethics Institute's The State of AI Ethics captures the most relevant developments in AI Ethics since October 2020.
Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention
This work shows the ability to learn dexterous manipulation behaviors in the real world with RL without any human intervention.
Making Responsible AI the Norm rather than the Exception
This report prepared by the Montreal AI Ethics Institute provides recommendations in response to the National Security Commission on Artificial Intelligence (NSCAI) Key Considerations for Responsible Development and Fielding of Artificial Intelligence document.
Coverage Analysis of Broadcast Networks with Users Having Heterogeneous Content/Advertisement Preferences
With the help of numerical results and analysis, we show the impact of various parameters including content granularity, connectivity radius, and rate threshold and present important design insights.
Information Theory Information Theory
A Deep Reinforcement Learning Framework for Eco-driving in Connected and Automated Hybrid Electric Vehicles
Connected and Automated Vehicles (CAVs), in particular those with multiple power sources, have the potential to significantly reduce fuel consumption and travel time in real-world driving conditions.
Incentive Design and Profit Sharing in Multi-modal Transportation Network
Accordingly, in this paper, we use cooperative game theory coupled with the hyperpath-based stochastic user equilibrium framework to study such a market.
Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
In the context of solving differential equations, we are faced with the problem of finding globally optimum parameters of the network, instead of being concerned with out-of-sample generalization.
Reinforcement Learning with Bayesian Classifiers: Efficient Skill Learning from Outcome Examples
In this work, we study a more tractable class of reinforcement learning problems defined by data that provides examples of successful outcome states.
Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances
Under such settings, existing transfer evolutionary optimization frameworks grapple with simultaneously satisfying two important quality attributes, namely (1) scalability against a growing number of source tasks and (2) online learning agility against sparsity of relevant sources to the target task of interest.
The State of AI Ethics Report (October 2020)
The 2nd edition of the Montreal AI Ethics Institute's The State of AI Ethics captures the most relevant developments in the field of AI Ethics since July 2020.
Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks
Machine learning predictors have been increasingly applied in production settings, including in one of the world's largest hiring platforms, Hired, to provide a better candidate and recruiter experience.
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution.
Report prepared by the Montreal AI Ethics Institute (MAIEI) on Publication Norms for Responsible AI
In order to ensure that the science and technology of AI is developed in a humane manner, we must develop research publication norms that are informed by our growing understanding of AI's potential threats and use cases.
CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
The prevalence of machine learning models in various industries has led to growing demands for model interpretability and for the ability to provide meaningful recourse to users.
Adversary Agnostic Robust Deep Reinforcement Learning
Motivated by this finding, we propose a new policy distillation loss with two terms: 1) a prescription gap maximization loss aiming at simultaneously maximizing the likelihood of the action selected by the teacher policy and the entropy over the remaining actions; 2) a corresponding Jacobian regularization loss that minimizes the magnitude of the gradient with respect to the input state.
Report prepared by the Montreal AI Ethics Institute In Response to Mila's Proposal for a Contact Tracing App
Contact tracing has grown in popularity as a promising solution to the COVID-19 pandemic.
Green Lighting ML: Confidentiality, Integrity, and Availability of Machine Learning Systems in Deployment
In this hand-off, the engineers responsible for model deployment are often not privy to the details of the model and thus, the potential vulnerabilities associated with its usage, exposure, or compromise.
Adaptive Risk Minimization: Learning to Adapt to Domain Shift
A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution.
The State of AI Ethics Report (June 2020)
These past few months have been especially challenging, and the deployment of technology in ways hitherto untested at an unrivalled pace has left the internet and technology watchers aghast.
ByGARS: Byzantine SGD with Arbitrary Number of Attackers
We show that using these reputation scores for gradient aggregation is robust to any number of multiplicative noise Byzantine adversaries and use two-timescale stochastic approximation theory to prove convergence for strongly convex loss functions.
Ecological Reinforcement Learning
Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions.
Response by the Montreal AI Ethics Institute to the European Commission's Whitepaper on AI
This paper outlines the EC's policy options for the promotion and adoption of artificial intelligence (AI) in the European Union.
AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
If we can instead allow RL algorithms to effectively use previously collected data to aid the online learning process, such applications could be made substantially more practical: the prior data would provide a starting point that mitigates challenges due to exploration and sample complexity, while the online training enables the agent to perfect the desired skill.
The Social Contract for AI
It is important to keep in mind that for AI, meeting the expectations of this social contract is critical, because recklessly driving the adoption and implementation of unsafe, irresponsible, or unethical AI systems may trigger serious backlash against industry and academia involved which could take decades to resolve, if not actually seriously harm society.
SECure: A Social and Environmental Certificate for AI Systems
In a world increasingly dominated by AI applications, an understudied aspect is the carbon and social footprint of these power-hungry algorithms that require copious computation and a trove of data for training and prediction.
Road Grade Estimation Using Crowd-Sourced Smartphone Data
Estimates of road grade/slope can add another dimension of information to existing 2D digital road maps.
The Ingredients of Real World Robotic Reinforcement Learning
The success of reinforcement learning in the real world has been limited to instrumented laboratory scenarios, often requiring arduous human supervision to enable continuous learning.
The Ingredients of Real-World Robotic Reinforcement Learning
In this work, we discuss the elements that are needed for a robotic learning system that can continually and autonomously improve with data collected in the real world.
Steady-state fluctuations of a genetic feedback loop with fluctuating rate parameters using the unified colored noise approximation
A common model of stochastic auto-regulatory gene expression describes promoter switching via cooperative protein binding, effective protein production in the active state and dilution of proteins.
Convergence of Recursive Stochastic Algorithms using Wasserstein Divergence
We show that if the distribution of the iterates in the Markov chain satisfy a contraction property with respect to the Wasserstein divergence, then the Markov chain admits an invariant distribution.
DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from this corrective feedback, and training on the experience collected by the algorithm is not sufficient to correct errors in the Q-function.
Ranked #3 on
Meta-Learning
on MT50
Learning in Markov Decision Processes under Constraints
In order to measure the performance of a reinforcement learning algorithm that satisfies the average cost constraints, we define an $M+1$ dimensional regret vector that is composed of its reward regret, and $M$ cost regrets.
Gradient Surgery for Multi-Task Learning
While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge.
Learning to Reach Goals via Iterated Supervised Learning
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards.
Multi-Goal Reinforcement Learning
Reinforcement Learning (RL)
Unsupervised Curricula for Visual Meta-Reinforcement Learning
In experiments on vision-based navigation and manipulation domains, we show that the algorithm allows for unsupervised meta-learning that transfers to downstream tasks specified by hand-crafted reward functions and serves as pre-training for more efficient supervised meta-learning of test task distributions.
A Multi-Task Gradient Descent Method for Multi-Label Learning
Multi-label learning studies the problem where an instance is associated with a set of labels.
Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy
Recent studies have revealed that neural network-based policies can be easily fooled by adversarial examples.
Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks.
Distributed SGD Generalizes Well Under Asynchrony
The performance of fully synchronized distributed systems has faced a bottleneck due to the big data trend, under which asynchronous distributed systems are becoming a major popularity due to their powerful scalability.
ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots
ROBEL introduces two robots, each aimed to accelerate reinforcement learning research in different task domains: D'Claw is a three-fingered hand robot that facilitates learning dexterous manipulation tasks, and D'Kitty is a four-legged robot that facilitates learning agile legged locomotion tasks.
Mint: Matrix-Interleaving for Multi-Task Learning
Deep learning enables training of large and flexible function approximators from scratch at the cost of large amounts of data.
Learning to Reach Goals Without Reinforcement Learning
By maximizing the likelihood of good actions provided by an expert demonstrator, supervised imitation learning can produce effective policies without the algorithmic complexities and optimization challenges of reinforcement learning, at the cost of requiring an expert demonstrator -- typically a person -- to provide the demonstrations.
Canada Protocol: an ethical checklist for the use of Artificial Intelligence in Suicide Prevention and Mental Health
Objectives: The Canada Protocol - MHSP is a tool to guide and support professionals, users, and researchers using AI in mental health and suicide prevention.
Learning latent state representation for speeding up exploration
In this work, we take a representation learning viewpoint on exploration, utilizing prior experience to learn effective latent representations, which can subsequently indicate which regions to explore.
Learning to Reinforcement Learn by Imitation
Meta-reinforcement learning aims to learn fast reinforcement learning (RL) procedures that can be applied to new tasks or environments.
Learning Actionable Representations with Goal Conditioned Policies
Most prior work on representation learning has focused on generative approaches, learning representations that capture all the underlying factors of variation in the observation space in a more disentangled or well-ordered manner.
Some Limit Properties of Markov Chains Induced by Stochastic Recursive Algorithms
We show that starting from the same initial condition, the distribution of the random sequence generated by the iterated random operators converges weakly to the trajectory generated by the contraction operator.
Guided Meta-Policy Search
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch.
Domain Randomization for Active Pose Estimation
In this work, we investigate how to improve the accuracy of domain randomization based pose estimation.
AIR5: Five Pillars of Artificial Intelligence Research
In this article, we provide and overview of what we consider to be some of the most pressing research questions facing the fields of artificial intelligence (AI) and computational intelligence (CI); with the latter focusing on algorithms that are inspired by various natural phenomena.
Soft Actor-Critic Algorithms and Applications
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
Learning Actionable Representations with Goal-Conditioned Policies
Most prior work on representation learning has focused on generative approaches, learning representations that capture all underlying factors of variation in the observation space in a more disentangled or well-ordered manner.
Guiding Policies with Language via Meta-Learning
However, a single instruction may be insufficient to fully communicate our intent or, even if it is, may be insufficient for an autonomous agent to actually understand how to perform the desired task.
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost
Dexterous multi-fingered robotic hands can perform a wide range of manipulation skills, making them an appealing component for general-purpose robotic manipulators.
Adversarial Reinforcement Learning for Observer Design in Autonomous Systems under Cyber Attacks
Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc.
Automatically Composing Representation Transformations as a Means for Generalization
A generally intelligent learner should generalize to more complex tasks than it has previously encountered, but the two common paradigms in machine learning -- either training a separate learner per task or training a single learner for all tasks -- both have difficulty with such generalization because they do not leverage the compositional structure of the task distribution.
Unsupervised Meta-Learning for Reinforcement Learning
In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks.
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
We show that we can learn continuous latent representations of trajectories, which are effective in solving temporally extended and multi-stage problems.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Probabilistic Contraction Analysis of Iterated Random Operators
In many branches of engineering, Banach contraction mapping theorem is employed to establish the convergence of certain deterministic algorithms.
Meta-Reinforcement Learning of Structured Exploration Strategies
Exploration is a fundamental challenge in reinforcement learning (RL).
Diversity is All You Need: Learning Skills without a Reward Function
On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping.
Addressing Expensive Multi-objective Games with Postponed Preference Articulation via Memetic Co-evolution
This paper presents algorithmic and empirical contributions demonstrating that the convergence characteristics of a co-evolutionary approach to tackle Multi-Objective Games (MOGs) with postponed preference articulation can often be hampered due to the possible emergence of the so-called Red Queen effect.
Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency.
From Query-By-Keyword to Query-By-Example: LinkedIn Talent Search Approach
One key challenge in talent search is to translate complex criteria of a hiring position into a search query, while it is relatively easy for a searcher to list examples of suitable candidates for a given position.
Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator.
Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results
In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously.
Evolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results
In this report, we suggest nine test problems for multi-task multi-objective optimization (MTMOO), each of which consists of two multiobjective optimization tasks that need to be solved simultaneously.
Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures.
Learning Dexterous Manipulation Policies from Experience and Imitation
We demonstrate that such controllers can perform the task robustly, both in simulation and on the physical platform, for a limited range of initial conditions around the trained starting state.
Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer
Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy classes, but exacerbates the challenge of data collection, since such methods tend to be less efficient than RL with low-dimensional, hand-designed representations.
Genetic Transfer or Population Diversification? Deciphering the Secret Ingredients of Evolutionary Multitask Optimization
Evolutionary multitasking has recently emerged as a novel paradigm that enables the similarities and/or latent complementarities (if present) between distinct optimization tasks to be exploited in an autonomous manner simply by solving them together with a unified solution representation scheme.
Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration
In this paper, we describe an approach to learning from demonstration that can be used to train soft robotic hands to perform dexterous manipulation tasks.
Search by Ideal Candidates: Next Generation of Talent Search at LinkedIn
This new system only needs the searcher to input one or several examples of suitable candidates for the position.
