Research map / Reinforcement learning / Visual and representation RL
Maximum State Entropy Exploration using Predecessor and Successor Representations
Arnav Kumar Jain, Lucas Lehnert, Irina Rish, Glen Berseth
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 non-Markovian ηψ-Learning instead of Markovian MaxEnt policy | ηψ-Learning · discrete environments | entropy of state visitation: 20-50% higher entropy | Improved |
| Use ηψ-Learning instead of MaxEnt | RL exploration · TwoRooms and FourRooms | state coverage: MaxEnt around 50-60% | Improved |
| Use ηψ-Learning instead of MaxEnt | RL exploration · Reacher | state coverage: 50 -> 90 | Improved |
| Use ηψ-Learning instead of MaxEnt | RL exploration · Pusher | state coverage: 40 -> 90 | Improved |
| Use ηψ-Learning instead of MaxEnt | RL exploration · all discrete environments | search completion time | Improved |
| Use ηψ-Learning instead of MaxEnt | RL exploration · FourRooms | search completion time | No clear effect |
| Use ηψ-Learning instead of VariBAD | exploration · state coverage and goal search time | state coverage | Improved |
Closest papers by meaning
- Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate (AAAI 2021 · similarity 0.88)
- Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration (NeurIPS 2023 · similarity 0.88)
- Exploration by Learning Diverse Skills through Successor State Representations (NeurIPS 2024 · similarity 0.87)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.86)
- Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- How to Explore with Belief: State Entropy Maximization in POMDPs (ICML 2024 · similarity 0.85)
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.
