Research map / Multi-agent systems and games / Games and equilibria
Deep Reinforcement Learning for General Game Playing
Adrian Goldwaser, Michael Thielscher
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 |
|---|---|---|---|
| set value target mix r to 0.5 (blend of final result and search value) versus r=0 or r=1 (ablation) | Generalised AlphaZero · Connect-4 6x7 vs UCT | games won vs UCT | Improved |
| use Generalised AlphaZero instead of UCT | Breakthrough 6x6 · Breakthrough 6x6 | games won vs UCT (out of 50): 49-50 out of 50 | Improved |
| use Generalised AlphaZero instead of UCT | Pacman 3p · Pacman 3p | reward | Improved |
| use Generalised AlphaZero instead of UCT | Babel (cooperative) · Babel | average reward per player | Hurt |
Closest papers by meaning
- Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract) (AAAI 2024 · similarity 0.88)
- Enhancing Chess Reinforcement Learning with Graph Representation (NeurIPS 2024 · similarity 0.87)
- Efficient Learning for AlphaZero via Path Consistency (ICML 2022 · similarity 0.86)
- Neural Auto-Curricula in Two-Player Zero-Sum Games (NeurIPS 2021 · similarity 0.85)
- Learning to Play No-Press Diplomacy with Best Response Policy Iteration (NeurIPS 2020 · similarity 0.85)
- Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics (NeurIPS 2025 · similarity 0.84)
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.
