Model-Based RL

Robust Transfer Learning With Side Information UAI 2026 Infinite-Horizon Reinforcement Learning with Multinomial Logit Function Approximation AISTATS 2025 Learning to Steer Markovian Agents under Model Uncertainty ICLR 2025 MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning AAAI 2025 Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds ICLR 2025 On Rollouts in Model-Based Reinforcement Learning ICLR 2025 StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs ACL 2025 Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning NeurIPS 2024 Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning NeurIPS 2024 Simplifying Latent Dynamics with Softly State-Invariant World Models NeurIPS 2024 Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models EMNLP 2023 Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning ICLR 2023 Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting ICLR 2023 KURL: A Knowledge-Guided Reinforcement Learning Model for Active Object Tracking ACML 2023 Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning AAAI 2023 Multi-Step Generalized Policy Improvement by Leveraging Approximate Models NeurIPS 2023 Planning and Learning for Non-markovian Negative Side Effects Using Finite State Controllers AAAI 2023 Posterior Sampling for Deep Reinforcement Learning ICML 2023 Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective ICLR 2023 Thinker: Learning to Plan and Act NeurIPS 2023 Approximate Value Equivalence NeurIPS 2022 A Unified Framework for Alternating Offline Model Training and Policy Learning NeurIPS 2022 Gradient Information Matters in Policy Optimization by Back-propagating through Model ICLR 2022 Learning Probably Approximately Complete and Safe Action Models for Stochastic Worlds AAAI 2022 MoCoDA: Model-based Counterfactual Data Augmentation NeurIPS 2022