Research map / Reinforcement learning / MDPs and planning
DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning
Archana Bura, Aria Hasanzadezonuzy, Dileep Kalathil, Srinivas Shakkottai, Jean-Francois Chamberland
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 |
|---|---|---|---|
| combine model optimism and reward optimism with pessimistic constraints | DOPE · Finite-horizon CMDP | objective regret: reduces the objective regret bound over OptPessLP by a factor of \sqrt{|\mathcal{S}|} | Improved |
| use DOPE instead of OptPess-LP | Factored CMDP · Factored CMDP | objective regret | Improved |
| use DOPE instead of OptCMDP | Factored CMDP · Factored CMDP | constraint regret | Improved |
| use DOPE instead of OptPess-LP | Media Streaming CMDP · Media Streaming CMDP | objective regret | Improved |
| use DOPE instead of OptCMDP | Media Streaming CMDP · Media Streaming CMDP | constraint regret | Improved |
| use a less conservative safe baseline policy (ablation) | DOPE · Factored CMDP and Media Streaming CMDP | objective regret | Improved |
| use AlwaysSafe π_α instead of AlwaysSafe π_T (ablation) | AlwaysSafe · Factored CMDP | objective regret | Improved |
Closest papers by meaning
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.91)
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 2024 · similarity 0.91)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.91)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.91)
- Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis (AAAI 2024 · similarity 0.91)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.90)
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.
