Reinforcement Learning

Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon COLT 2021 Iterative Amortized Policy Optimization NeurIPS 2021 Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods AAAI 2021 Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning CVPR 2021 Language Representations for Generalization in Reinforcement Learning ACML 2021 Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations NeurIPS 2021 Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs NeurIPS 2021 Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation ICLR 2021 Learning to Reach Goals via Iterated Supervised Learning ICLR 2021 Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning AAAI 2021 Learning to Sample with Local and Global Contexts in Experience Replay Buffer ICLR 2021 Learning to Set Waypoints for Audio-Visual Navigation ICLR 2021 Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control AAAI 2021 Learning Value Functions in Deep Policy Gradients using Residual Variance ICLR 2021 Learning What To Do by Simulating the Past ICLR 2021 Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs AAAI 2021 Lipschitz Lifelong Reinforcement Learning AAAI 2021 LOA: Logical Optimal Actions for Text-based Interaction Games ACL 2021 MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents NeurIPS 2021 Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning AAAI 2021 Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes AAAI 2021 Model-Based Visual Planning with Self-Supervised Functional Distances ICLR 2021 Monte-Carlo Planning and Learning with Language Action Value Estimates ICLR 2021 Multi-task Actor-Critic with Knowledge Transfer via a Shared Critic ACML 2021 Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes COLT 2021