Reinforcement Learning

Memory Gym: Partially Observable Challenges to Memory-Based Agents ICLR 2023 MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations ICLR 2023 Multi-Agent First Order Constrained Optimization in Policy Space NeurIPS 2023 Multi-Level Compositional Reasoning for Interactive Instruction Following AAAI 2023 Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto Optimality ICLR 2023 Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation NeurIPS 2023 Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation ICLR 2023 Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication ICLR 2023 Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching AAAI 2023 Offline Imitation Learning with Variational Counterfactual Reasoning NeurIPS 2023 On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes NeurIPS 2023 Online Reinforcement Learning in Stochastic Continuous-Time Systems COLT 2023 On the Robustness of Safe Reinforcement Learning under Observational Perturbations ICLR 2023 On the Sensitivity of Reward Inference to Misspecified Human Models ICLR 2023 Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates NeurIPS 2023 PAC Reinforcement Learning for Predictive State Representations ICLR 2023 PAL to Lend a Helping Hand: Towards Building an Emotion Adaptive Polite and Empathetic Counseling Conversational Agent ACL 2023 Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition NeurIPS 2023 Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs ICLR 2023 Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning ICLR 2023 Planning and Learning with Adaptive Lookahead AAAI 2023 Planning with Sequence Models through Iterative Energy Minimization ICLR 2023 Policy-Independent Behavioral Metric-Based Representation for Deep Reinforcement Learning AAAI 2023 POPGym: Benchmarking Partially Observable Reinforcement Learning ICLR 2023 Powderworld: A Platform for Understanding Generalization via Rich Task Distributions ICLR 2023