AI Paper Atlas

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

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Novelty and impact-driven exploration · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use non-Markovian ηψ-Learning instead of Markovian MaxEnt policyηψ-Learning · discrete environmentsentropy of state visitation: 20-50% higher entropyImproved
Use ηψ-Learning instead of MaxEntRL exploration · TwoRooms and FourRoomsstate coverage: MaxEnt around 50-60%Improved
Use ηψ-Learning instead of MaxEntRL exploration · Reacherstate coverage: 50 -> 90Improved
Use ηψ-Learning instead of MaxEntRL exploration · Pusherstate coverage: 40 -> 90Improved
Use ηψ-Learning instead of MaxEntRL exploration · all discrete environmentssearch completion timeImproved
Use ηψ-Learning instead of MaxEntRL exploration · FourRoomssearch completion timeNo clear effect
Use ηψ-Learning instead of VariBADexploration · state coverage and goal search timestate coverageImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy