Research map / Reinforcement learning / MDPs and planning
Provably Efficient Maximum Entropy Exploration
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 MaxEnt exploration instead of choosing actions randomly | MountainCar · MountainCar | entropy of induced state distribution | Helped |
| Use MaxEnt exploration instead of choosing actions randomly | Pendulum · Pendulum | entropy of induced state distribution | Helped |
| Use MaxEnt exploration instead of choosing actions randomly | Ant · Ant | entropy of induced state distribution | Helped |
| Increase the number of policies in the mixture | MaxEnt agent · Ant | number of distinct xy states visited | Helped |
| Use MaxEnt exploration | MaxEnt agent · MountainCar, Pendulum, and Ant | reachable-state coverage | Helped |
Closest papers by meaning
- Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate (AAAI 2021 · similarity 0.90)
- Fast Rates for Maximum Entropy Exploration (ICML 2023 · similarity 0.90)
- How to Explore with Belief: State Entropy Maximization in POMDPs (ICML 2024 · similarity 0.88)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.87)
- Near-Optimal Sample Complexity for MDPs via Anchoring (ICML 2025 · similarity 0.87)
- Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction (ICML 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.