Methods

PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training ICML 2021 PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators NeurIPS 2021 Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL NeurIPS 2021 PettingZoo: Gym for Multi-Agent Reinforcement Learning NeurIPS 2021 Phasic Policy Gradient ICML 2021 Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks ICLR 2021 Planning from Pixels in Atari with Learned Symbolic Representations AAAI 2021 Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration IJCAI 2021 PODS: Policy Optimization via Differentiable Simulation ICML 2021 Policy Caches with Successor Features ICML 2021 Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning NeurIPS 2021 Policy Gradient Bayesian Robust Optimization for Imitation Learning ICML 2021 Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning ICML 2021 Policy Learning Using Weak Supervision NeurIPS 2021 Policy Learning with Constraints in Model-free Reinforcement Learning: A Survey IJCAI 2021 Policy Optimization as Online Learning with Mediator Feedback AAAI 2021 Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses NeurIPS 2021 Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks JMLR 2021 Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods ICML 2021 Predicting Human Scanpaths in Visual Question Answering CVPR 2021 Prediction and generalisation over directed actions by grid cells ICLR 2021 Preferential Temporal Difference Learning ICML 2021 Primal-dual Learning for the Model-free Risk-constrained Linear Quadratic Regulator L4DC 2021 Principled Exploration via Optimistic Bootstrapping and Backward Induction ICML 2021 Prioritized Level Replay ICML 2021