Research map / Reinforcement learning / Visual and representation RL
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning
Kimin Lee, Younggyo Seo, Seunghyun Lee, Honglak Lee, Jinwoo Shin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add CaDM to PE-TS | PE-TS · HalfCheetah test (moderate) | average return: 2019.6 to 7087.2 | Improved |
| Add CaDM to Vanilla DM | Vanilla DM · CartPole test (moderate) | average return: 124.7 to 154.3 | Improved |
| Add CaDM to PE-TS | PE-TS · CartPole test (moderate) | average return: 171.3 to 187.3 | Improved |
| Add CaDM to Vanilla DM | Vanilla DM · Pendulum test (moderate) | average return: -928.4 to -593.7 | Improved |
| Add CaDM to PE-TS | PE-TS · Pendulum test (moderate) | average return: -985.7 to -705.5 | Improved |
| Add CaDM to PE-TS | PE-TS · Ant test (moderate) | average return: 1075.1 to 2121.0 | Improved |
| Add CaDM to PE-TS | PE-TS · CrippledHalfCheetah test (moderate) | average return: 1916.5 to 2618.7 | Improved |
| Add CaDM to Vanilla DM | Vanilla DM · SlimHumanoid test (moderate) | average return: 1004.4 to 1228.9 | Improved |
| Condition PPO on the CaDM context vector | PPO · HalfCheetah test (moderate) | average return: 895.3 to 1224.2 | Improved |
| Condition PPO on the CaDM context vector | PPO · Ant test (moderate) | average return: 207.0 to 228.8 | Improved |
| Condition PPO on the CaDM context vector | PPO · CrippledHalfCheetah test (moderate) | average return: 1162.2 to 1454.0 | Improved |
| Condition PPO on the CaDM context vector | PPO · SlimHumanoid test (moderate) | average return: 3928.5 to 4975.7 | Improved |
Closest papers by meaning
- Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts (NeurIPS 2025 · similarity 0.89)
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity (NeurIPS 2024 · similarity 0.89)
- Model-Based Transfer Learning for Contextual Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
