Research map / Reinforcement learning / Visual and representation RL
State Abstractions for Lifelong 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 |
|---|---|---|---|
| hand-coded room state abstraction (φh) added to Q-learning and Delayed-Q | Q-Learning and Delayed-Q · Colored Four Rooms (11x11) | cumulative reward | Hurt |
| PAC Q-based state abstractions added to Q-Learning | Q-Learning · Colored Four Rooms (11x11) | cumulative reward | Helped |
| approximate Q abstraction φQ*ε added to Delayed-Q | Delayed-Q · Four Room (30x30) | cumulative reward | Hurt |
| approximate Q abstraction φQ*ε added to R-Max | R-Max · 3-chain MDP | cumulative reward | Hurt |
| transitive PAC abstraction φQ*d added to Delayed-Q | Delayed-Q · Four Room (30x30) | cumulative reward | No clear effect |
| state abstraction for value iteration planning (vi-φQ*d vs vi) | Value Iteration · Upworld and Trench planning | planning time | Helped |
Closest papers by meaning
- Generalisation in Lifelong Reinforcement Learning through Logical Composition (ICLR 2022 · similarity 0.91)
- Policy and Value Transfer in Lifelong Reinforcement Learning (ICML 2018 · similarity 0.90)
- Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning (AAAI 2025 · similarity 0.90)
- Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Learning Generalizable and Composable Abstractions for Transfer in Reinforcement Learning (AAAI 2024 · similarity 0.88)
- Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning (AAAI 2024 · 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.