Research map / Reinforcement learning / MDPs and planning
Multi-View Reinforcement Learning
Minne Li, Lisheng Wu, Jun WANG, Haitham Bou Ammar
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 |
|---|---|---|---|
| Use MV-MB instead of PILCO | Model-based Cartpole control · Cartpole | interactions till success: 240 -> 381 ± 28 | Hurt |
| Use MV-MB instead of PILCO-aug | Model-based Cartpole control · Cartpole | interactions till success: 320 -> 381 ± 28 | Hurt |
| Use MV-MB instead of an MLP dynamics model | Model-based Cartpole control · Cartpole | interactions till success: 2334 ± 358 -> 381 ± 28 | Improved |
| Augment PPO with concatenated observations from multiple views | Model-free multi-view policy learning · Cartpole and parking | average testing return | Improved |
| Transfer a policy across views using a learned multi-view model | MV-PT · Cartpole, Hopper, RACECAR, and parking | training samples to reach good performance: around two orders of magnitudes | Improved |
| Use a single PILCO model on augmented states from all views (ablation) | PILCO · Cartpole | interactions till success: 240 -> 320 | Hurt |
Closest papers by meaning
- Learning Fused State Representations for Control from Multi-View Observations (ICML 2025 · similarity 0.89)
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.87)
- Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight (ICLR 2024 · similarity 0.86)
- Model-Based Exploration in Monitored Markov Decision Processes (ICML 2025 · similarity 0.85)
- RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation (NeurIPS 2024 · similarity 0.85)
- Offline RL with Observation Histories: Analyzing and Improving Sample Complexity (ICLR 2024 · similarity 0.85)
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.
