Search Results for author:
Found 57 papers, 24 papers with code
Trajectory VAE for multi-modal imitation
In this paper, we use a generative model to capture different emergent playstyles in an unsupervised manner, enabling the imitation of a diverse range of distinct behaviours.
Learning Safety Constraints from Demonstrations with Unknown Rewards
We propose Convex Constraint Learning for Reinforcement Learning (CoCoRL), a novel approach for inferring shared constraints in a Constrained Markov Decision Process (CMDP) from a set of safe demonstrations with possibly different reward functions.
Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
We aim to understand how people assess human likeness in navigation produced by people and artificially intelligent (AI) agents in a video game.
Trust-Region-Free Policy Optimization for Stochastic Policies
In this paper, we show that the trust region constraint over policies can be safely substituted by a trust-region-free constraint without compromising the underlying monotonic improvement guarantee.
Imitating Human Behaviour with Diffusion Models
This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments.
UniMASK: Unified Inference in Sequential Decision Problems
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks.
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
In this paper we push this Pareto frontier in the few-shot image classification setting with a key contribution: a new adaptive block called Contextual Squeeze-and-Excitation (CaSE) that adjusts a pretrained neural network on a new task to significantly improve performance with a single forward pass of the user data (context).
Ranked #3 on
Few-Shot Image Classification
on Meta-Dataset
Interactively Learning Preference Constraints in Linear Bandits
We provide an instance-dependent lower bound for constrained linear best-arm identification and show that ACOL's sample complexity matches the lower bound in the worst-case.
Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021
The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment.
Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks.
You May Not Need Ratio Clipping in PPO
Furthermore, we show that ESPO can be easily scaled up to distributed training with many workers, delivering strong performance as well.
Trust Region Bounds for Decentralized PPO Under Non-stationarity
We present trust region bounds for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL), which holds even when the transition dynamics are non-stationary.
Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency
Sample efficiency is crucial for imitation learning methods to be applicable in real-world applications.
NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions.
Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning
High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems.
SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
In this paper, we argue that aiming towards human-level AI requires a broader set of key social skills: 1) language use in complex and variable social contexts; 2) beyond language, complex embodied communication in multimodal settings within constantly evolving social worlds.
Memory Efficient Meta-Learning with Large Images
This limitation arises because a task's entire support set, which can contain up to 1000 images, must be processed before an optimization step can be taken.
Grounding Spatio-Temporal Language with Transformers
While there is an extended literature studying how machines can learn grounded language, the topic of how to learn spatio-temporal linguistic concepts is still largely uncharted.
SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching
We present SoftDICE, which achieves state-of-the-art performance for imitation learning.
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness.
SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI.
ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
To close this gap, we present the ORBIT dataset and benchmark, grounded in the real-world application of teachable object recognizers for people who are blind/low-vision.
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
Training autonomous agents able to generalize to multiple tasks is a key target of Deep Reinforcement Learning (DRL) research.
Evaluating the Robustness of Collaborative Agents
We apply this methodology to build a suite of unit tests for the Overcooked-AI environment, and use this test suite to evaluate three proposals for improving robustness.
Deep Interactive Bayesian Reinforcement Learning via Meta-Learning
The optimal adaptive behaviour under uncertainty over the other agents' strategies w. r. t.
Meta Automatic Curriculum Learning
In such complex task spaces, it is essential to rely on some form of Automatic Curriculum Learning (ACL) to adapt the task sampling distribution to a given learning agent, instead of randomly sampling tasks, as many could end up being either trivial or unfeasible.
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
To rapidly learn a new task, it is often essential for agents to explore efficiently -- especially when performance matters from the first timestep.
"It's Unwieldy and It Takes a Lot of Time." Challenges and Opportunities for Creating Agents in Commercial Games
We compare with literature from the research community that address the challenges identified and conclude by highlighting promising directions for future research supporting agent creation in the games industry.
Analytic Manifold Learning: Unifying and Evaluating Representations for Continuous Control
Our second contribution is a unifying mathematical formulation for learning latent relations.
Guaranteeing Reproducibility in Deep Learning Competitions
To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance of their learning procedures rather than pre-trained agents.
Conservative Uncertainty Estimation By Fitting Prior Networks
Obtaining high-quality uncertainty estimates is essential for many applications of deep neural networks.
AMRL: Aggregated Memory For Reinforcement Learning
In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.
SpatialSim: Recognizing Spatial Configurations of Objects with Graph Neural Networks
Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far.
Trying AGAIN instead of Trying Longer: Prior Learning for Automatic Curriculum Learning
A major challenge in the Deep RL (DRL) community is to train agents able to generalize over unseen situations, which is often approached by training them on a diversity of tasks (or environments).
Automatic Curriculum Learning For Deep RL: A Short Survey
Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL). These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities.
Better Exploration with Optimistic Actor Critic
To address both of these phenomena, we introduce a new algorithm, Optimistic Actor Critic, which approximates a lower and upper confidence bound on the state-action value function.
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
We discuss those differences and propose modifications to existing regularization techniques in order to better adapt them to RL.
Better Exploration with Optimistic Actor-Critic
To address both of these phenomena, we introduce a new algorithm, Optimistic Actor Critic, which approximates a lower and upper confidence bound on the state-action value function.
Variational Integrator Networks for Physically Structured Embeddings
Learning workable representations of dynamical systems is becoming an increasingly important problem in a number of application areas.
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning.
Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments.
Combining No-regret and Q-learning
Counterfactual Regret Minimization (CFR) has found success in settings like poker which have both terminal states and perfect recall.
Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games
We study two-player general sum repeated finite games where the rewards of each player are generated from an unknown distribution.
The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors
To that end, we introduce: (1) the Minecraft ObtainDiamond task, a sequential decision making environment requiring long-term planning, hierarchical control, and efficient exploration methods; and (2) the MineRL-v0 dataset, a large-scale collection of over 60 million state-action pairs of human demonstrations that can be resimulated into embodied trajectories with arbitrary modifications to game state and visuals.
The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition
Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning.
Fast Context Adaptation via Meta-Learning
We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable.
CAML: Fast Context Adaptation via Meta-Learning
We propose CAML, a meta-learning method for fast adaptation that partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared parameters that are meta-trained and shared across tasks.
Depth and nonlinearity induce implicit exploration for RL
The question of how to explore, i. e., take actions with uncertain outcomes to learn about possible future rewards, is a key question in reinforcement learning (RL).
Variational Inference for Data-Efficient Model Learning in POMDPs
In this paper we propose DELIP, an approach to model learning for POMDPs that utilizes amortized structured variational inference.
Cross Domain Regularization for Neural Ranking Models Using Adversarial Learning
We use an adversarial discriminator and train our neural ranking model on a small set of domains.
Information Retrieval
Meta Reinforcement Learning with Latent Variable Gaussian Processes
Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e. g., robotics, animal experiments or drug design.
The Atari Grand Challenge Dataset
Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environments, yet real-world applications of RL are still scarce.
A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown.
Memory Lens: How Much Memory Does an Agent Use?
The study of memory as information that flows from the past to the current action opens avenues to understand and improve successful reinforcement learning algorithms.
Experimental and causal view on information integration in autonomous agents
The amount of digitally available but heterogeneous information about the world is remarkable, and new technologies such as self-driving cars, smart homes, or the internet of things may further increase it.
Contextual Dueling Bandits
The first of these algorithms achieves particularly low regret, even when data is adversarial, although its time and space requirements are linear in the size of the policy space.
