Policy Learning

Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity ICML 2025 Convergence and Sample Complexity of Natural Policy Gradient Primal-Dual Methods for Constrained MDPs JMLR 2025 Convergence of Policy Mirror Descent Beyond Compatible Function Approximation ICML 2025 COPR: Continual Human Preference Learning via Optimal Policy Regularization ACL 2025 Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking ICLR 2025 Cost-Aware Near-Optimal Policy Learning AAAI 2025 Counterfactual Influence in Markov Decision Processes CLeaR 2025 Counterfactual Strategies for Markov Decision Processes IJCAI 2025 CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization EMNLP 2025 Data Augmentation for Instruction Following Policies via Trajectory Segmentation AAAI 2025 Data-Driven Near-Optimal Control of Nonlinear Systems Over Finite Horizon L4DC 2025 Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning EMNLP 2025 Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning AAAI 2025 Deep Electromagnetic Structure Design Under Limited Evaluation Budgets ICML 2025 Deep Implicit Imitation Reinforcement Learning in Heterogeneous Action Settings AAAI 2025 Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning AAAI 2025 Demonstration Selection for In-Context Learning via Reinforcement Learning ICML 2025 DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration CoRL 2025 Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation ICML 2025 Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs AAAI 2025 Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference Scoped Exploration CoRL 2025 DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control ICML 2025 DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation CoRL 2025 Diffusion Policy Policy Optimization ICLR 2025 DIME: Diffusion-Based Maximum Entropy Reinforcement Learning ICML 2025