Research map / Learning theory and algorithms / Combinatorial and search optimization
Beyond Monte Carlo Tree Search: Playing Go with Deep Alternative Neural Network and Long-Term Evaluation
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 |
|---|---|---|---|
| Replace standard convolutional layers with alternative layers (ablation) | Go move prediction · GoGoD and PGD | top-1 accuracy: 32.2% -> 53.5%; 37.2% -> 51.8% | Helped |
| Add alternative layers in place of convolutional layers (ablation) | DANN move predictor · GoGoD and PGD | top-1 accuracy: 40.5% -> 53.5%; 42.5% -> 51.8% | Helped |
| Increase recurrent unfolding time from T = 2 to T = 5 (ablation) | 5AL_2FC · GoGoD and PGD | top-1 accuracy: 46.9% -> 55.0%; 42.3% -> 51.6% | Helped |
| Increase recurrent unfolding time from T = 2 to T = 5 (ablation) | 6AL_2FC · GoGoD and PGD | top-1 accuracy: 46.4% -> 57.7%; 47.2% -> 53.8% | Mixed |
| Combine candidate probabilities with long-term evaluation of future rewards | DANN · GoGoD and PGD | top-1 accuracy: 61%; 56% | Helped |
| Add local response normalization (ablation) | DANN · Move prediction | accuracy | Helped |
Closest papers by meaning
- Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search (AAAI 2021 · similarity 0.90)
- Learning to search with MCTSnets (ICML 2018 · similarity 0.88)
- Monte Carlo Tree Search with Boltzmann Exploration (NeurIPS 2023 · similarity 0.86)
- Speculative Monte-Carlo Tree Search (NeurIPS 2024 · similarity 0.85)
- ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning (ICLR 2025 · similarity 0.84)
- Evidence of Learned Look-Ahead in a Chess-Playing Neural Network (NeurIPS 2024 · 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.