Research map / Reinforcement learning / MDPs and planning
A Unifying View of Optimism in Episodic Reinforcement Learning
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 nested-subset confidence constraints instead of UCRL2's transition confidence sets | Optimistic LP planning for episodic MDPs · Episodic MDPs | regret upper bound: UCRL2: \redd{C}HS\sqrt{AT} + 2H\sqrt{2T\log(1/\delta)} -> \widetilde{O}(H\sqrt{SAT}) | Helped |
| Use empirical Bernstein confidence bounds instead of UCRL2's confidence bounds | Optimistic LP planning for episodic MDPs · Episodic MDPs | regret upper bound: UCRL2: \redd{C}HS\sqrt{AT} + 2H\sqrt{2T\log(1/\delta)}; BOLP: \widetilde O (S \sqrt{HAT}) | Helped |
Closest papers by meaning
- Optimism in Reinforcement Learning with Generalized Linear Function Approximation (ICLR 2021 · similarity 0.92)
- Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning (NeurIPS 2020 · similarity 0.91)
- Bayesian Optimistic Optimization: Optimistic Exploration for Model-based Reinforcement Learning (NeurIPS 2022 · similarity 0.91)
- Minimax Optimal Reinforcement Learning with Quasi-Optimism (ICLR 2025 · similarity 0.90)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.89)
- Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling (ICLR 2025 · similarity 0.88)
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.