Offline Reinforcement Learning with Soft Behavior Regularization Oct 14, 2021 continuous-control Continuous Control
— Unverified Planning from Pixels in Environments with Combinatorially Hard Search Spaces Oct 12, 2021 continuous-control Continuous Control
Code Code Available Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization Oct 10, 2021 continuous-control Continuous Control
— Unverified Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning Oct 7, 2021 Continuous Control Deep Reinforcement Learning
— Unverified Cross-Domain Imitation Learning via Optimal Transport Oct 7, 2021 continuous-control Continuous Control
Code Code Available Evaluating model-based planning and planner amortization for continuous control Oct 7, 2021 continuous-control Continuous Control
— Unverified Continuous-Time Fitted Value Iteration for Robust Policies Oct 5, 2021 continuous-control Continuous Control
Code Code Available Meta Attention For Off-Policy Actor-Critic Sep 29, 2021 continuous-control Continuous Control
— Unverified Graph-Enhanced Exploration for Goal-oriented Reinforcement Learning Sep 29, 2021 continuous-control Continuous Control
— Unverified State-Only Imitation Learning by Trajectory Distribution Matching Sep 29, 2021 continuous-control Continuous Control
— Unverified Reward Shifting for Optimistic Exploration and Conservative Exploitation Sep 29, 2021 continuous-control Continuous Control
— Unverified Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning Sep 29, 2021 Clustering continuous-control
— Unverified Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning Sep 29, 2021 continuous-control Continuous Control
— Unverified Imitation Learning from Pixel Observations for Continuous Control Sep 29, 2021 Benchmarking continuous-control
— Unverified Gradient Information Matters in Policy Optimization by Back-propagating through Model Sep 29, 2021 continuous-control Continuous Control
Code Code Available Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts Sep 29, 2021 Autonomous Driving continuous-control
— Unverified Why so pessimistic? Estimating uncertainties for offline RL through ensembles, and why their independence matters. Sep 29, 2021 continuous-control Continuous Control
— Unverified Decentralized Cross-Entropy Method for Model-Based Reinforcement Learning Sep 29, 2021 continuous-control Continuous Control
— Unverified Faster Reinforcement Learning with Value Target Lower Bounding Sep 29, 2021 Atari Games continuous-control
— Unverified Evaluating Robustness of Cooperative MARL Sep 29, 2021 continuous-control Continuous Control
— Unverified Distributional Decision Transformer for Hindsight Information Matching Sep 29, 2021 continuous-control Continuous Control
— Unverified Generalizing Successor Features to continuous domains for Multi-task Learning Sep 29, 2021 continuous-control Continuous Control
— Unverified Joint Self-Supervised Learning for Vision-based Reinforcement Learning Sep 29, 2021 Autonomous Driving continuous-control
— Unverified Transformers are Meta-Reinforcement Learners Sep 29, 2021 continuous-control Continuous Control
— Unverified An Experimental Design Perspective on Exploration in Reinforcement Learning Sep 29, 2021 continuous-control Continuous Control
— Unverified SPLID: Self-Imitation Policy Learning through Iterative Distillation Sep 29, 2021 continuous-control Continuous Control
— Unverified Effects of Conservatism on Offline Learning Sep 29, 2021 continuous-control Continuous Control
— Unverified Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning Sep 29, 2021 continuous-control Continuous Control
— Unverified Exploring More When It Needs in Deep Reinforcement Learning Sep 28, 2021 continuous-control Continuous Control
— Unverified Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience Sep 24, 2021 continuous-control Continuous Control
— Unverified Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients Sep 24, 2021 continuous-control Continuous Control
Code Code Available Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods Sep 22, 2021 continuous-control Continuous Control
Code Code Available Federated Ensemble Model-based Reinforcement Learning in Edge Computing Sep 12, 2021 Autonomous Driving continuous-control
— Unverified Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning Sep 8, 2021 Adversarial Attack continuous-control
— Unverified ADER:Adapting between Exploration and Robustness for Actor-Critic Methods Sep 8, 2021 continuous-control Continuous Control
— Unverified Error Controlled Actor-Critic Sep 6, 2021 continuous-control Continuous Control
Code Code Available Photonic Quantum Policy Learning in OpenAI Gym Aug 29, 2021 BIG-bench Machine Learning continuous-control
— Unverified HAC Explore: Accelerating Exploration with Hierarchical Reinforcement Learning Aug 12, 2021 continuous-control Continuous Control
— Unverified Imitation Learning by Reinforcement Learning Aug 10, 2021 continuous-control Continuous Control
Code Code Available Value-Based Reinforcement Learning for Continuous Control Robotic Manipulation in Multi-Task Sparse Reward Settings Jul 28, 2021 continuous-control Continuous Control
— Unverified Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning Jul 20, 2021 continuous-control Continuous Control
Code Code Available Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks Jul 13, 2021 continuous-control Continuous Control
Code Code Available Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing Jul 12, 2021 continuous-control Continuous Control
Code Code Available Cautious Actor-Critic Jul 12, 2021 continuous-control Continuous Control
— Unverified Coordinate-wise Control Variates for Deep Policy Gradients Jul 11, 2021 continuous-control Continuous Control
— Unverified Imitation by Predicting Observations Jul 8, 2021 continuous-control Continuous Control
— Unverified Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation Jul 5, 2021 continuous-control Continuous Control
Code Code Available SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments Jul 1, 2021 continuous-control Continuous Control
— Unverified Continuous Control with Deep Reinforcement Learning for Autonomous Vessels Jun 27, 2021 Collision Avoidance continuous-control
— Unverified Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice Jun 26, 2021 continuous-control Continuous Control
Code Code Available 