Research map / Reinforcement learning / Visual and representation RL
From Observations to Events: Event-Aware World Models for Reinforcement Learning
Zhao-Han Peng, Shaohui Li, Zhi Li, Shulan Ruan, Yu LIU, You He
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 event-aware representation learning (EAWM) | Simulus · Atari 100K | Mean HNS: 1.609 -> 1.818 | Improved |
| add event-aware representation learning (EAWM) | DreamerV3 · Atari 100K | Mean HNS: 1.150 -> 1.290 | Improved |
| add EAWM | DreamerV3 · Atari 100K | Optimality gap: 0.501 -> 0.474 | No clear effect |
| add EAWM | DreamerV3 · DMC hard tasks | Mean score: 606.3 -> 723.8 | Improved |
| add EAWM | DreamerV3 · DMC-GB2 | score | Improved |
| add EAWM | Simulus · Craftax 1M | score: 7.23% | Improved |
| add the event predictor (ablation) | EADream and EASimulus · Atari 6-game subset | Mean HNS: about 0.4 drop when removed | Improved |
| add gated event signal (GES) (ablation) | EAWM · Atari and DMC ablation | Median HNS | Improved |
| predict observations directly (observation prediction) instead of reconstruction (ablation) | EAWM · DMC 4 tasks | Mean score: 519.5 -> 737.2 | Improved |
| use RSSM-OP alone without events (ablation) | DreamerV3 · DMC | score | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CURL — CURL: Contrastive Unsupervised Representations for Reinforcement Learning (ICML 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RLVR-World: Training World Models with Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields (NeurIPS 2026 · similarity 0.87)
- AdaWorld: Learning Adaptable World Models with Latent Actions (ICML 2025 · similarity 0.87)
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.86)
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning (ICLR 2025 · similarity 0.86)
- From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction (NeurIPS 2025 · similarity 0.86)
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.
