Policy Learning

Residual Q-Learning: Offline and Online Policy Customization without Value NeurIPS 2023 Revisiting Bellman Errors for Offline Model Selection ICML 2023 Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning NeurIPS 2023 Reward-machine-guided, self-paced reinforcement learning UAI 2023 Reward-Mixing MDPs with Few Latent Contexts are Learnable ICML 2023 Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks NeurIPS 2023 Risk-aware curriculum generation for heavy-tailed task distributions UAI 2023 Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models RSS 2023 Robust Average-Reward Markov Decision Processes AAAI 2023 Robust Satisficing MDPs ICML 2023 RRHF: Rank Responses to Align Language Models with Human Feedback NeurIPS 2023 SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations NeurIPS 2023 Safe Policy Improvement for POMDPs via Finite-State Controllers AAAI 2023 Safe Reinforcement Learning via Probabilistic Logic Shields IJCAI 2023 Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees IJCAI 2023 Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks NeurIPS 2023 Scalable Safe Policy Improvement via Monte Carlo Tree Search ICML 2023 Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning CoRL 2023 Self-Predictive Universal AI NeurIPS 2023 Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation CoRL 2023 Simultaneously Updating All Persistence Values in Reinforcement Learning AAAI 2023 Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees JMLR 2023 SKD-NER: Continual Named Entity Recognition via Span-based Knowledge Distillation with Reinforcement Learning EMNLP 2023 Soft Action Priors: Towards Robust Policy Transfer AAAI 2023 Solving multi-model MDPs by coordinate ascent and dynamic programming UAI 2023