Research map / Reinforcement learning / Offline RL
Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning
Guy Tennenholtz, Shie Mannor
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 |
|---|---|---|---|
| Use the pullback metric rather than latent ℓ2 distance (ablation) | GELATO · D4RL continuous control | return: Hopper med: 1320 -> 1676; Walker2d med: 312 -> 1269; Hopper med-expert: 815 -> 574 | Mixed |
| Use the pullback metric rather than bootstrap ensemble uncertainty | GELATO vs MOPO · D4RL continuous control | return: Hopper med: 1202 -> 1676; HalfCheetah rand: 4114 -> 2560 | Mixed |
| Use the pullback metric rather than latent Euclidean distance (ablation) | GELATO · Autonomous driving benchmarks | return | Improved |
| Use the pullback metric rather than standard uncertainty estimation methods | GELATO · Autonomous driving benchmarks | return | Improved |
| Use the pullback metric for uncertainty estimation | GELATO · Autonomous driving benchmarks | runtime: 5 times slower | Hurt |
| Train the variance decoder in a separate second phase after calibrated Gaussian decoding | GELATO variational model · D4RL | convergence speed and accuracy | Improved |
| Use geodesic distance instead of latent Euclidean distance | GELATO distance visualization · Four Rooms | distance fidelity | Improved |
| Use geodesic rather than Euclidean distances for the embedding | GELATO visualization · Intersection | structure captured | Improved |
Closest papers by meaning
- SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning (AAAI 2025 · similarity 0.88)
- A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch (NeurIPS 2024 · similarity 0.88)
- Dynamic Uncertainty Estimation for Offline Reinforcement Learning (AAAI 2025 · similarity 0.87)
- Selective Uncertainty Propagation in Offline RL (AAAI 2025 · similarity 0.87)
- Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning (NeurIPS 2024 · 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.
