Methods

Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning AISTATS 2021 A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning JMLR 2021 A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning NeurIPS 2021 A Provably Efficient Sample Collection Strategy for Reinforcement Learning NeurIPS 2021 APS: Active Pretraining with Successor Features ICML 2021 A Regret Minimization Approach to Iterative Learning Control ICML 2021 A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints AAAI 2021 A Sharp Analysis of Model-based Reinforcement Learning with Self-Play ICML 2021 Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models NeurIPS 2021 Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment ICML 2021 Augmenting Policy Learning with Routines Discovered from a Single Demonstration AAAI 2021 A Universal 2-state n-action Adaptive Management Solver AAAI 2021 A User-Adaptive Layer Selection Framework for Very Deep Sequential Recommender Models AAAI 2021 Automatically Exposing Problems with Neural Dialog Models EMNLP 2021 Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning AAAI 2021 Auto-Navigator: Decoupled Neural Architecture Search for Visual Navigation WACV 2021 Autonomous Reinforcement Learning via Subgoal Curricula NeurIPS 2021 Auxiliary Tasks for Efficient Learning of Point-Goal Navigation WACV 2021 Average-Reward Learning and Planning with Options NeurIPS 2021 Average-Reward Off-Policy Policy Evaluation with Function Approximation ICML 2021 Average-Reward Reinforcement Learning with Trust Region Methods IJCAI 2021 A Workflow for Offline Model-Free Robotic Reinforcement Learning CoRL 2021 BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning IJCAI 2021 Balancing Constraints and Rewards with Meta-Gradient D4PG ICLR 2021 Batch Reinforcement Learning Through Continuation Method ICLR 2021