Research map / Reinforcement learning / Visual and representation RL
Provable Sim-to-real Transfer in Continuous Domain with Partial Observations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 robust adversarial training instead of a trivial policy | Sim-to-real transfer · Continuous domain with partial observations | sim-to-real gap: O(H) -> \tilde{O}(\sqrt{H}) | Helped |
| Use a simpler simulator class under the realizability assumption | Robust adversarial training policy (π_RT) · Continuous-domain sim-to-real transfer with partial observations | sim-to-real gap | Helped |
| Train a policy only in simulation | Sim-to-real transfer · Continuous domain with partial observations | sim-to-real gap: \Omega(\sqrt{H}) | Mixed |
Closest papers by meaning
- EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer (NeurIPS 2024 · similarity 0.88)
- Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL (NeurIPS 2024 · similarity 0.88)
- SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer (NeurIPS 2025 · similarity 0.85)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.85)
- Adversarial Diffusion for Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.85)
- Transfer Q-Learning with Composite MDP Structures (ICML 2025 · similarity 0.84)
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.