Research map / Reinforcement learning / Visual and representation RL
Coordinated Exploration in Concurrent Reinforcement Learning
Maria Dimakopoulou, Benjamin Van Roy
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 seed sampling instead of concurrent UCRL | Concurrent reinforcement learning · Maximum Reward Path | cumulative regret: 49.9% higher cumulative regret | Improved |
| Use seed sampling instead of Thompson resampling | Concurrent reinforcement learning · Maximum Reward Path | cumulative regret: 191% higher cumulative regret | Improved |
| Use concurrent UCRL instead of seed sampling | Concurrent reinforcement learning · Parallel Chains | mean regret per agent: 100 agents vs. 100,000 agents | Hurt |
| Resample an MDP independently at every time period rather than keep a fixed seed | Thompson resampling · Bipolar Chain | mean regret per agent | Hurt |
| Use concurrent UCRL rather than seed sampling | Concurrent reinforcement learning · Bipolar Chain | mean regret per agent | Improved |
| Use Thompson resampling rather than seed sampling | Concurrent reinforcement learning · Parallel Chains | mean regret per agent | No clear effect |
Closest papers by meaning
- Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing (AAAI 2024 · similarity 0.88)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.87)
- Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story (ICML 2025 · similarity 0.86)
- The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration (NeurIPS 2026 · similarity 0.86)
- Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration (NeurIPS 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.
