Research map / Reinforcement learning / Visual and representation RL
Composable Modular 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 |
|---|---|---|---|
| scale AvoidWolf module reward by 10 (incomparable module reward scales) (ablation) | GM-Sarsa / Q-decomposition · Bunny-Wolf world | average score per time step | Hurt |
| scale AvoidWolf module reward by 10 (incomparable module reward scales) (ablation) | Arbi-Q · Bunny-Wolf world | average score per time step | No clear effect |
| use Q-learning instead of Sarsa for modules and arbitrator (ablation) | Arbi-Q · Bunny-Wolf world | average score per time step | No clear effect |
| replace additive Q-value arbitration (GM-Sarsa) with learned Q-learning arbitrator (Arbi-Q) under comparable reward scales | modular RL agent · Bunny-Wolf world | average score per time step | No clear effect |
Closest papers by meaning
- Assume-Guarantee Reinforcement Learning (AAAI 2024 · similarity 0.86)
- Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints (ICML 2024 · similarity 0.84)
- O-MAPL: Offline Multi-agent Preference Learning (ICML 2025 · similarity 0.83)
- On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning (ICLR 2024 · similarity 0.83)
- Decoding Global Preferences: Temporal and Cooperative Dependency Modeling in Multi-Agent Preference-Based Reinforcement Learning (AAAI 2024 · similarity 0.83)
- Asymptotic Extinction in Large Coordination Games (AAAI 2025 · similarity 0.83)
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.