Search Results for author:
Found 55 papers, 25 papers with code
Seeing the Unseen: How EMoE Unveils Bias in Text-to-Image Diffusion Models
In this paper, we propose Epistemic Mixture of Experts (EMoE), a novel framework for efficiently estimating epistemic uncertainty in diffusion models.
Tractable Representations for Convergent Approximation of Distributional HJB Equations
Recent work has established a distributional HJB (DHJB) equation, providing the first characterization of return distributions in CTRL.
Fairness in Reinforcement Learning with Bisimulation Metrics
Ensuring long-term fairness is crucial when developing automated decision making systems, specifically in dynamic and sequential environments.
Parseval Regularization for Continual Reinforcement Learning
Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the increased difficulty in training on new tasks.
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
Whether the performance of distributional RL (DRL) agents suffers similarly, however, is unknown.
Distributional Reinforcement Learning
reinforcement-learning
+2
Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models
Generative diffusion models, notable for their large parameter count (exceeding 100 million) and operation within high-dimensional image spaces, pose significant challenges for traditional uncertainty estimation methods due to computational demands.
Constrained Robotic Navigation on Preferred Terrains Using LLMs and Speech Instruction: Exploiting the Power of Adverbs
This paper explores leveraging large language models for map-free off-road navigation using generative AI, reducing the need for traditional data collection and annotation.
Learning active tactile perception through belief-space control
These robots will need to sense these properties through interaction prior to performing downstream tasks with the objects.
Generalizable Imitation Learning Through Pre-Trained Representations
In this paper, we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies.
Imitation Learning from Observation through Optimal Transport
We demonstrate the effectiveness of this simple approach on a variety of continuous control tasks and find that it surpasses the state of the art in the IlfO setting, achieving expert-level performance across a range of evaluation domains even when observing only a single expert trajectory without actions.
Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning
In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentangled World Model to address the challenge of achieving a common goal of multiple agents interacting in the same environment with reduced sample complexity.
Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators
This work introduces an efficient novel approach for epistemic uncertainty estimation for ensemble models for regression tasks using pairwise-distance estimators (PaiDEs).
For SALE: State-Action Representation Learning for Deep Reinforcement Learning
In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems.
Policy Gradient Methods in the Presence of Symmetries and State Abstractions
Our policy gradient results allow for leveraging approximate symmetries of the environment for policy optimization.
Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling
In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions.
Hypernetworks for Zero-shot Transfer in Reinforcement Learning
In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks.
NeurIPS 2022 Competition: Driving SMARTS
The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.
Uncertainty-Driven Active Vision for Implicit Scene Reconstruction
We evaluate our proposed approach on the ABC dataset and the in the wild CO3D dataset, and show that: (1) we are able to obtain high quality state-of-the-art occupancy reconstructions; (2) our perspective conditioned uncertainty definition is effective to drive improvements in next best view selection and outperforms strong baseline approaches; and (3) we can further improve shape understanding by performing a gradient-based search on the view selection candidates.
Bayesian Q-learning With Imperfect Expert Demonstrations
Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information.
Continuous MDP Homomorphisms and Homomorphic Policy Gradient
Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms.
Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning
We demonstrate the effectiveness of such an algorithm in a synthetic control problem.
IL-flOw: Imitation Learning from Observation using Normalizing Flows
We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only.
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error
In this work, we study the use of the Bellman equation as a surrogate objective for value prediction accuracy.
Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain
We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks.
Why Should I Trust You, Bellman? Evaluating the Bellman Objective with Off-Policy Data
In this work, we analyze the effectiveness of the Bellman equation as a proxy objective for value prediction accuracy in off-policy evaluation.
Generalizing Successor Features to continuous domains for Multi-task Learning
In this paper, we consider the problem of continuous control for various robot manipulation tasks with an explicit representation that promotes skill reuse while learning multiple tasks, related through the reward function.
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning
Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.
Active 3D Shape Reconstruction from Vision and Touch
In this paper, we focus on this problem and introduce a system composed of: 1) a haptic simulator leveraging high spatial resolution vision-based tactile sensors for active touching of 3D objects; 2)a mesh-based 3D shape reconstruction model that relies on tactile or visuotactile signals; and 3) a set of data-driven solutions with either tactile or visuotactile priors to guide the shape exploration.
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation
We bridge the gap between MIS and deep reinforcement learning by observing that the density ratio can be computed from the successor representation of the target policy.
Learning Intuitive Physics with Multimodal Generative Models
Predicting the future interaction of objects when they come into contact with their environment is key for autonomous agents to take intelligent and anticipatory actions.
Practical Marginalized Importance Sampling with the Successor Representation
We bridge the gap between MIS and deep reinforcement learning by observing that the density ratio can be computed from the successor representation of the target policy.
Intervention Design for Effective Sim2Real Transfer
The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting.
Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference
Utilization of latent space to capture a lower-dimensional representation of a complex dynamics model is explored in this work.
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-uniform probability proportionate to their temporal-difference error.
3D Shape Reconstruction from Vision and Touch
When a toddler is presented a new toy, their instinctual behaviour is to pick it upand inspect it with their hand and eyes in tandem, clearly searching over its surface to properly understand what they are playing with.
Learning to Drive Off Road on Smooth Terrain in Unstructured Environments Using an On-Board Camera and Sparse Aerial Images
We present a method for learning to drive on smooth terrain while simultaneously avoiding collisions in challenging off-road and unstructured outdoor environments using only visual inputs.
Detecting GAN generated errors
This is because the task of evaluating the quality of a generated image differs from deciding if an image is real or fake.
Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales
PAC Bayes is a generalized framework which is more resistant to overfitting and that yields performance bounds that hold with arbitrarily high probability even on the unjustified extrapolations.
Deep learning for Aerosol Forecasting
Reanalysis datasets combining numerical physics models and limited observations to generate a synthesised estimate of variables in an Earth system, are prone to biases against ground truth.
Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning
Motivated by the recursive Newton-Euler formulation, we propose a novel cascaded Gaussian process learning framework for the inverse dynamics of robot manipulators.
Learning Domain Randomization Distributions for Training Robust Locomotion Policies
We explore the use of gradient-based search methods to learn a domain randomization with the following properties: 1) The trained policy should be successful in environments sampled from the domain randomization distribution 2) The domain randomization distribution should be wide enough so that the experience similar to the target robot system is observed during training, while addressing the practicality of training finite capacity models.
Human Motion Prediction via Pattern Completion in Latent Representation Space
Inspired by ideas in cognitive science, we propose a novel and general approach to solve human motion understanding via pattern completion on a learned latent representation space.
Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks
Learned controllers such as neural networks typically do not have a notion of uncertainty that allows to diagnose an offset between training and testing conditions, and potentially intervene.
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Mesh models are a promising approach for encoding the structure of 3D objects.
Ranked #1 on
3D Object Reconstruction
on Data3D−R2N2
(Avg F1 metric)
Off-Policy Deep Reinforcement Learning without Exploration
Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection.
Where Off-Policy Deep Reinforcement Learning Fails
This work examines batch reinforcement learning--the task of maximally exploiting a given batch of off-policy data, without further data collection.
Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning
Finally, we assess the performance of the algorithm for learning motor controllers for a six legged autonomous underwater vehicle.
Model-based Reinforcement Learning
reinforcement-learning
+2
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation
We consider the problem of scaling deep generative shape models to high-resolution.
Ranked #2 on
3D Object Reconstruction
on Data3D−R2N2
(Avg F1 metric)
Addressing Function Approximation Error in Actor-Critic Methods
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies.
Ranked #2 on
OpenAI Gym
on Ant-v4
Bayesian Policy Gradients via Alpha Divergence Dropout Inference
Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult.
Cost Adaptation for Robust Decentralized Swarm Behaviour
To allay this problem, we use a meta-learning process -- cost adaptation -- which generates the optimization objective for D-RHC to solve based on a set of human-generated priors (cost and constraint functions) and an auxiliary heuristic.
OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations.
Deep Reinforcement Learning that Matters
In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning (RL).
Benchmark Environments for Multitask Learning in Continuous Domains
As demand drives systems to generalize to various domains and problems, the study of multitask, transfer and lifelong learning has become an increasingly important pursuit.
Improved Adversarial Systems for 3D Object Generation and Reconstruction
This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects.
