Ching-An Cheng

Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning ICLR 2025 How to Solve Contextual Goal-Oriented Problems with Offline Datasets? NeurIPS 2024 Improving Offline RL by Blending Heuristics ICLR 2024 PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control ICML 2024 Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs NeurIPS 2024 Adversarial Model for Offline Reinforcement Learning NeurIPS 2023 Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control CoRL 2023 Hindsight Learning for MDPs with Exogenous Inputs ICML 2023 MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations ICML 2023 PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining CoRL 2023 Provable Reset-free Reinforcement Learning by No-Regret Reduction ICML 2023 Provably Efficient Lifelong Reinforcement Learning with Linear Representation ICLR 2023 Survival Instinct in Offline Reinforcement Learning NeurIPS 2023 Adversarially Trained Actor Critic for Offline Reinforcement Learning ICML 2022 MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control NeurIPS 2022 Bellman-consistent Pessimism for Offline Reinforcement Learning NeurIPS 2021 Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation COLT 2021 Explaining fast improvement in online imitation learning UAI 2021 Heuristic-Guided Reinforcement Learning NeurIPS 2021 RMP2: A Structured Composable Policy Class for Robot Learning RSS 2021 Safe Reinforcement Learning Using Advantage-Based Intervention ICML 2021 A Reduction from Reinforcement Learning to No-Regret Online Learning AISTATS 2020 Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks NeurIPS 2020 Online Learning with Continuous Variations: Dynamic Regret and Reductions AISTATS 2020 Policy Improvement via Imitation of Multiple Oracles NeurIPS 2020 Accelerating Imitation Learning with Predictive Models AISTATS 2019 An Online Learning Approach to Model Predictive Control RSS 2019 Predictor-Corrector Policy Optimization ICML 2019 Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping CoRL 2019 Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods CoRL 2019 Truncated Back-propagation for Bilevel Optimization AISTATS 2019 Agile Autonomous Driving using End-to-End Deep Imitation Learning RSS 2018 Convergence of Value Aggregation for Imitation Learning AISTATS 2018 Orthogonally Decoupled Variational Gaussian Processes NeurIPS 2018 Variational Inference for Gaussian Process Models with Linear Complexity NeurIPS 2017 Incremental Variational Sparse Gaussian Process Regression NeurIPS 2016