Research map / Reinforcement learning / MDPs and planning
Feedback-Based Tree Search for 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 |
|---|---|---|---|
| Use feedback-based tree search instead of direct policy iteration | King of Glory 1v1 · Six marksman opponents | frames to defeat | Helped |
| Use feedback-based tree search instead of approximate value iteration | King of Glory 1v1 · Six marksman opponents | frames to defeat | Helped |
| Use feedback-based tree search instead of supervised learning on human gameplay | King of Glory 1v1 · Six marksman opponents | frames to defeat | Helped |
| Use feedback-based tree search instead of the internal DiRenJie AI | King of Glory 1v1 · Six marksman opponents | frames to defeat | Helped |
| Add partial policy rollouts to tree-search leaf evaluation (ablation) | FBTS · King of Glory 1v1, common opponents | frames to defeat | Helped |
| Use feedback-based tree search instead of no-rollout tree search | King of Glory 1v1 · Head-to-head against four baselines | gold ratio: 1.25 to 1.75 | Helped |
Closest papers by meaning
- Online Robust Reinforcement Learning Through Monte-Carlo Planning (ICML 2025 · similarity 0.89)
- MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning (NeurIPS 2025 · similarity 0.88)
- Monte Carlo Planning with Large Language Model for Text-Based Game Agents (ICLR 2025 · similarity 0.87)
- ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning (ICLR 2025 · similarity 0.87)
- SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes (NeurIPS 2025 · similarity 0.87)
- Efficient Multi-agent Reinforcement Learning by Planning (ICLR 2024 · similarity 0.87)
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.