Copertina

Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Czech, Johannes, Blüml, Jannis, Kersting, Kristian, Steingrimsson, Hedinn
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess
di: Helfenstein, Felix, et al.
Pubblicazione: (2024)

Diversifying AI: Towards Creative Chess with AlphaZero
di: Zahavy, Tom, et al.
Pubblicazione: (2023)

AlphaZero-Edu: Democratizing Access to AlphaZero
di: Li, Ruitong, et al.
Pubblicazione: (2025)

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
di: Delfosse, Quentin, et al.
Pubblicazione: (2024)

Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown
di: Derstroff, Cedric, et al.
Pubblicazione: (2024)

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
di: Delfosse, Quentin, et al.
Pubblicazione: (2023)

Improving Robustness of AlphaZero Algorithms to Test-Time Environment Changes
di: Tamassia, Isidoro, et al.
Pubblicazione: (2025)

Deep Reinforcement Learning via Object-Centric Attention
di: Blüml, Jannis, et al.
Pubblicazione: (2025)

Better Decisions through the Right Causal World Model
di: Dillies, Elisabeth, et al.
Pubblicazione: (2025)

Regret-Guided Search Control for Efficient Learning in AlphaZero
di: Tsai, Yun-Jui, et al.
Pubblicazione: (2026)

MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
di: Wu, Ti-Rong, et al.
Pubblicazione: (2023)

Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
di: Mehrabian, Abbas, et al.
Pubblicazione: (2023)

Boosting deep Reinforcement Learning using pretraining with Logical Options
di: Ye, Zihan, et al.
Pubblicazione: (2026)

MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games
di: Li, Qian-Rong, et al.
Pubblicazione: (2026)

Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
di: Zollicoffer, Geigh, et al.
Pubblicazione: (2024)

Deep Reinforcement Learning Agents are not even close to Human Intelligence
di: Delfosse, Quentin, et al.
Pubblicazione: (2025)

Reactive Knowledge Representation and Asynchronous Reasoning
di: Kohaut, Simon, et al.
Pubblicazione: (2026)

Search-contempt: a hybrid MCTS algorithm for training AlphaZero-like engines with better computational efficiency
di: Joshi, Ameya
Pubblicazione: (2025)

TSS GAZ PTP: Towards Improving Gumbel AlphaZero with Two-stage Self-play for Multi-constrained Electric Vehicle Routing Problems
di: Wang, Hui, et al.
Pubblicazione: (2025)

Mastering NIM and Impartial Games with Weak Neural Networks: An AlphaZero-inspired Multi-Frame Approach
di: Riis, Søren
Pubblicazione: (2024)

Enhancing Chess Reinforcement Learning with Graph Representation
di: Rigaux, Tomas, et al.
Pubblicazione: (2024)

Tractable Representation Learning with Probabilistic Circuits
di: Braun, Steven, et al.
Pubblicazione: (2025)

Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions
di: Cömer, Can, et al.
Pubblicazione: (2025)

A Behavior-Based Knowledge Representation Improves Prediction of Players' Moves in Chess by 25%
di: Skidanov, Benny, et al.
Pubblicazione: (2025)

Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning
di: Praski, Mateusz, et al.
Pubblicazione: (2025)

Complete Chess Games Enable LLM Become A Chess Master
di: Zhang, Yinqi, et al.
Pubblicazione: (2025)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
di: Deiseroth, Björn, et al.
Pubblicazione: (2024)

Grounded Chess Reasoning in Language Models via Master Distillation
di: Tang, Zhenwei, et al.
Pubblicazione: (2026)

Mastering Chinese Chess AI (Xiangqi) Without Search
di: Chen, Yu, et al.
Pubblicazione: (2024)

Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver
di: Sherwood, Joshua, et al.
Pubblicazione: (2026)

Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning
di: Ye, Zihan, et al.
Pubblicazione: (2025)

Interpretable end-to-end Neurosymbolic Reinforcement Learning agents
di: Grandien, Nils, et al.
Pubblicazione: (2024)

Adaptable Hindsight Experience Replay for Search-Based Learning
di: Vazaios, Alexandros, et al.
Pubblicazione: (2025)

Mixture of Masters: Sparse Chess Language Models with Player Routing
di: Frisoni, Giacomo, et al.
Pubblicazione: (2026)

Language-Independent Representations Improve Zero-Shot Summarization
di: Solovyev, Vladimir, et al.
Pubblicazione: (2024)

Systems with Switching Causal Relations: A Meta-Causal Perspective
di: Willig, Moritz, et al.
Pubblicazione: (2024)

Deep Classifier Mimicry without Data Access
di: Braun, Steven, et al.
Pubblicazione: (2023)

Core Tokensets for Data-efficient Sequential Training of Transformers
di: Paul, Subarnaduti, et al.
Pubblicazione: (2024)

Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers
di: Li, Quanhao, et al.
Pubblicazione: (2026)

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning
di: Hu, Xiao, et al.
Pubblicazione: (2025)