Image de couverture de livre

AlphaZeroES: Direct score maximization outperforms planning loss minimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Martin, Carlos, Sandholm, Tuomas
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ApproxED: Approximate exploitability descent via learned best responses
par: Martin, Carlos, et autres
Publié: (2023)

Domain-Independent Game Abstraction using Word Embedding Techniques
par: Kim, Juho, et autres
Publié: (2026)

Heuristic Pathologies and Further Variance Reduction via Uncertainty Propagation in the AIVAT Family of Techniques
par: Kim, Juho, et autres
Publié: (2026)

Parallelizing Counterfactual Regret Minimization
par: Kim, Juho, et autres
Publié: (2026)

General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess
par: Zhang, Brian Hu, et autres
Publié: (2025)

Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games
par: Kim, Juho, et autres
Publié: (2026)

AlphaZero-Edu: Democratizing Access to AlphaZero
par: Li, Ruitong, et autres
Publié: (2025)

Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation
par: Zhang, Brian, et autres
Publié: (2022)

Learning Potentials for Dynamic Matching and Application to Heart Transplantation
par: Zilberstein, Itai, et autres
Publié: (2026)

Near-Optimal Dynamic Matching via Coarsening with Application to Heart Transplantation
par: Zilberstein, Itai, et autres
Publié: (2026)

Game-Theoretic Multiagent Reinforcement Learning
par: Yang, Yaodong, et autres
Publié: (2020)

MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
par: Wu, Ti-Rong, et autres
Publié: (2023)

Diversifying AI: Towards Creative Chess with AlphaZero
par: Zahavy, Tom, et autres
Publié: (2023)

A multi-scale loss formulation for learning a probabilistic model with proper score optimisation
par: Lang, Simon, et autres
Publié: (2025)

Faster Optimal Coalition Structure Generation via Offline Coalition Selection and Graph-Based Search
par: Taguelmimt, Redha, et autres
Publié: (2024)

Alpha Zero for Physics: Application of Symbolic Regression with Alpha Zero to find the analytical methods in physics
par: Michishita, Yoshihiro
Publié: (2023)

Joint-perturbation simultaneous pseudo-gradient
par: Martin, Carlos, et autres
Publié: (2024)

Simultaneous incremental support adjustment and metagame solving: An equilibrium-finding framework for continuous-action games
par: Martin, Carlos, et autres
Publié: (2024)

Solving Infinite-Player Games with Player-to-Strategy Networks
par: Martin, Carlos, et autres
Publié: (2025)

AlphaMath Almost Zero: Process Supervision without Process
par: Chen, Guoxin, et autres
Publié: (2024)

Regret-Guided Search Control for Efficient Learning in AlphaZero
par: Tsai, Yun-Jui, et autres
Publié: (2026)

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
par: Liang, Yongyuan, et autres
Publié: (2023)

Improving Robustness of AlphaZero Algorithms to Test-Time Environment Changes
par: Tamassia, Isidoro, et autres
Publié: (2025)

Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers
par: Czech, Johannes, et autres
Publié: (2023)

Multi-agent AI systems outperform human teams in creativity
par: Hu, Tiancheng, et autres
Publié: (2026)

Zero loss guarantees and explicit minimizers for generic overparametrized Deep Learning networks
par: Chen, Thomas, et autres
Publié: (2025)

A Multiagent Path Search Algorithm for Large-Scale Coalition Structure Generation
par: Taguelmimt, Redha, et autres
Publié: (2025)

Convergence of $\text{log}(1/ε)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis
par: Anagnostides, Ioannis, et autres
Publié: (2024)

MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games
par: Li, Qian-Rong, et autres
Publié: (2026)

Exponential Lower Bounds on the Double Oracle Algorithm in Zero-Sum Games
par: Zhang, Brian Hu, et autres
Publié: (2024)

Code-enabled language models can outperform reasoning models on diverse tasks
par: Zhang, Cedegao E., et autres
Publié: (2025)

Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
par: Hou, Charlie, et autres
Publié: (2023)

Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
par: Mehrabian, Abbas, et autres
Publié: (2023)

AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
par: Wu, Junkang, et autres
Publié: (2024)

AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution
par: Guo, Taian, et autres
Publié: (2026)

Can OpenAI o1 outperform humans in higher-order cognitive thinking?
par: Latif, Ehsan, et autres
Publié: (2024)

Dual-attention ResNet outperforms transformers in HER2 prediction on DCE-MRI
par: Fridman, Naomi, et autres
Publié: (2025)

Towards Faster Matrix Diagonalization with Graph Isomorphism Networks and the AlphaZero Framework
par: Zollicoffer, Geigh, et autres
Publié: (2024)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
par: Jørgensen, Mikkel Godsk, et autres
Publié: (2026)

Scalable Mechanism Design for Multi-Agent Path Finding
par: Friedrich, Paul, et autres
Publié: (2024)