Deep RL

UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learning ICCV 2023 Uniformly Conservative Exploration in Reinforcement Learning AISTATS 2023 Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension UAI 2023 Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning AAAI 2023 Unsupervised Keyphrase Extraction by Learning Neural Keyphrase Set Function ACL 2023 User-Oriented Robust Reinforcement Learning AAAI 2023 User Simulator Assisted Open-ended Conversational Recommendation System ACL 2023 VA-learning as a more efficient alternative to Q-learning ICML 2023 Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning AAAI 2023 Variance Control for Distributional Reinforcement Learning ICML 2023 Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies NeurIPS 2023 Vessel-to-Vessel Motion Compensation with Reinforcement Learning AAAI 2023 Video Prediction Models as Rewards for Reinforcement Learning NeurIPS 2023 VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation ICLR 2023 VOQL: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation COLT 2023 Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap ICML 2023 Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control AAAI 2023 Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees ICLR 2023 Weakly Coupled Deep Q-Networks NeurIPS 2023 Weighted Sampling without Replacement for Deep Top-k Classification ICML 2023 What can online reinforcement learning with function approximation benefit from general coverage conditions? ICML 2023 When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment NeurIPS 2023 When is Agnostic Reinforcement Learning Statistically Tractable? NeurIPS 2023 When is Realizability Sufficient for Off-Policy Reinforcement Learning? ICML 2023 Why Target Networks Stabilise Temporal Difference Methods ICML 2023