Reinforcement Learning

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers ICLR 2021 OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning ICLR 2021 Optimal Policies Tend To Seek Power NeurIPS 2021 Optimism in Reinforcement Learning with Generalized Linear Function Approximation ICLR 2021 Outcome-Driven Reinforcement Learning via Variational Inference NeurIPS 2021 Parrot: Data-Driven Behavioral Priors for Reinforcement Learning ICLR 2021 Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses NeurIPS 2021 Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning NeurIPS 2021 Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature NeurIPS 2021 Quantifying Differences in Reward Functions ICLR 2021 Queue-Learning: A Reinforcement Learning Approach for Providing Quality of Service AAAI 2021 Randomized Ensembled Double Q-Learning: Learning Fast Without a Model ICLR 2021 ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models EMNLP 2021 Regret Minimization Experience Replay in Off-Policy Reinforcement Learning NeurIPS 2021 Reinforcement Learning Based Multi-Agent Resilient Control: From Deep Neural Networks to an Adaptive Law AAAI 2021 Reinforcement Learning in Newcomblike Environments NeurIPS 2021 Reinforcement Learning of Sequential Price Mechanisms AAAI 2021 Reinforcement Learning with Latent Flow NeurIPS 2021 Reinforcement Learning with Random Delays ICLR 2021 Relative Variational Intrinsic Control AAAI 2021 Reward based Hebbian Learning in Direct Feedback Alignment (Student Abstract) AAAI 2021 Robotic Manipulation with Reinforcement Learning, State Representation Learning, and Imitation Learning (Student Abstract) AAAI 2021 Robust Deep Reinforcement Learning through Adversarial Loss NeurIPS 2021 Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation ACML 2021 Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control ACML 2021