Deep RL

Parametrized Quantum Policies for Reinforcement Learning NeurIPS 2021 PatchMatch-RL: Deep MVS With Pixelwise Depth, Normal, and Visibility ICCV 2021 PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration ICML 2021 PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators 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 Policy Caches with Successor Features ICML 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 Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses NeurIPS 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 Principled Exploration via Optimistic Bootstrapping and Backward Induction ICML 2021 Prioritized Level Replay ICML 2021 Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics EMNLP 2021 Proper Value Equivalence NeurIPS 2021 Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature NeurIPS 2021 Provably Correct Optimization and Exploration with Non-linear Policies ICML 2021 Provably Efficient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic Case AISTATS 2021 Provably Efficient Causal Reinforcement Learning with Confounded Observational Data NeurIPS 2021 Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints NeurIPS 2021 Provably Efficient Safe Exploration via Primal-Dual Policy Optimization AISTATS 2021