Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning May 29, 2022 Continuous Control Deep Reinforcement Learning
— Unverified Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges May 28, 2022 Continual Learning Continuous Control
Code Code Available Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning May 28, 2022 Continuous Control Model-based Reinforcement Learning
— Unverified MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control May 26, 2022 continuous-control Continuous Control
Code Code Available SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning May 26, 2022 continuous-control Continuous Control
— Unverified Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning May 25, 2022 continuous-control Continuous Control
Code Code Available Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert Policies May 23, 2022 continuous-control Continuous Control
— Unverified IL-flOw: Imitation Learning from Observation using Normalizing Flows May 19, 2022 continuous-control Continuous Control
— Unverified Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks May 18, 2022 continuous-control Continuous Control
Code Code Available A cGAN Ensemble-based Uncertainty-aware Surrogate Model for Offline Model-based Optimization in Industrial Control Problems May 15, 2022 continuous-control Continuous Control
— Unverified A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning May 11, 2022 continuous-control Continuous Control
Code Code Available Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods May 8, 2022 continuous-control Continuous Control
Code Code Available Skill-based Meta-Reinforcement Learning Apr 25, 2022 continuous-control Continuous Control
— Unverified Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach Apr 21, 2022 continuous-control Continuous Control
— Unverified SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics Apr 20, 2022 continuous-control Continuous Control
— Unverified Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability Apr 8, 2022 continuous-control Continuous Control
— Unverified Automating Reinforcement Learning with Example-based Resets Apr 5, 2022 continuous-control Continuous Control
Code Code Available Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization Apr 4, 2022 continuous-control Continuous Control
— Unverified Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning Mar 24, 2022 continuous-control Continuous Control
— Unverified Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL Mar 21, 2022 continuous-control Continuous Control
— Unverified Multitask Neuroevolution for Reinforcement Learning with Long and Short Episodes Mar 21, 2022 continuous-control Continuous Control
— Unverified Multiscale Sensor Fusion and Continuous Control with Neural CDEs Mar 16, 2022 continuous-control Continuous Control
— Unverified Latent-Variable Advantage-Weighted Policy Optimization for Offline RL Mar 16, 2022 continuous-control Continuous Control
Code Code Available Temporal Difference Learning for Model Predictive Control Mar 9, 2022 continuous-control Continuous Control
Code Code Available Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation Feb 28, 2022 continuous-control Continuous Control
— Unverified Policy Learning and Evaluation with Randomized Quasi-Monte Carlo Feb 16, 2022 continuous-control Continuous Control
— Unverified Safe Reinforcement Learning by Imagining the Near Future Feb 15, 2022 continuous-control Continuous Control
Code Code Available Strategy Discovery and Mixture in Lifelong Learning from Heterogeneous Demonstration Feb 14, 2022 continuous-control Continuous Control
— Unverified Robust Learning from Observation with Model Misspecification Feb 12, 2022 continuous-control Continuous Control
Code Code Available Uncertainty Aware System Identification with Universal Policies Feb 11, 2022 Bayesian Optimisation continuous-control
— Unverified Imitation Learning by State-Only Distribution Matching Feb 9, 2022 continuous-control Continuous Control
Code Code Available Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning Feb 8, 2022 continuous-control Continuous Control
Code Code Available Approximate Policy Iteration with Bisimulation Metrics Feb 6, 2022 Continuous Control Representation Learning
Code Code Available Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning Feb 6, 2022 continuous-control Continuous Control
— Unverified Adversarially Trained Actor Critic for Offline Reinforcement Learning Feb 5, 2022 continuous-control Continuous Control
Code Code Available Learning Interpretable, High-Performing Policies for Autonomous Driving Feb 4, 2022 Autonomous Driving Autonomous Vehicles
Code Code Available Imitation Learning by Estimating Expertise of Demonstrators Feb 2, 2022 continuous-control Continuous Control
Code Code Available Adversarial Imitation Learning from Video using a State Observer Feb 1, 2022 continuous-control Continuous Control
— Unverified You May Not Need Ratio Clipping in PPO Jan 31, 2022 continuous-control Continuous Control
— Unverified DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning Jan 31, 2022 continuous-control Continuous Control
Code Code Available Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problems Jan 29, 2022 continuous-control Continuous Control
Code Code Available Robust Imitation Learning from Corrupted Demonstrations Jan 29, 2022 continuous-control Continuous Control
— Unverified Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications Jan 28, 2022 continuous-control Continuous Control
— Unverified State-Conditioned Adversarial Subgoal Generation Jan 24, 2022 continuous-control Continuous Control
— Unverified Recursive Least Squares Advantage Actor-Critic Algorithms Jan 15, 2022 Computational Efficiency continuous-control
— Unverified Evolutionary Action Selection for Gradient-based Policy Learning Jan 12, 2022 continuous-control Continuous Control
— Unverified Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation Jan 5, 2022 continuous-control Continuous Control
Code Code Available Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference Jan 2, 2022 continuous-control Continuous Control
Code Code Available A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning Jan 1, 2022 continuous-control Continuous Control
— Unverified Single-Shot Pruning for Offline Reinforcement Learning Dec 31, 2021 continuous-control Continuous Control
— Unverified 