mlsanityData to 7 Oct 2026

Particle Monte Carlo Tree Search

arXiv 2605.08982 ↗First posted 9 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement and action selection in Reinforcement Learning. Due to its sequential and deterministic nature, principled runtime-scaling of MCTS with parallel compute remains a major challenge. We introduce Particle MCTS (PMCTS), a parallel MCTS algorithm which is suited for neural network evaluations, designed for GPU-acceleration with batch-parallelization and retains MCTS's principled approximate policy improvement interpretation. Empirically, PMCTS scales well with parallel compute and consistently outperforms or compares well to the popular heuristic-based baselines across a range of popular discrete- and continuous-action benchmark domains, including Chess, 19x19 Go, 9x9 Go, Gardner Chess, Snake, classical control environments from Brax and LLM reasoning in Sokoban.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 49 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

20 of 49 references.

References · 20

  1. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  2. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  3. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  4. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 375
  5. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  6. 2021Learning and Planning in Complex Action Spacescited by 76
  7. 2020Monte-Carlo Tree Search as Regularized Policy Optimizationcited by 59
  8. 2023Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAXcited by 52
  9. 2023Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learningcited by 45
  10. 2024EfficientZero V2: Mastering Discrete and Continuous Control with Limited Datacited by 39
  11. 2025Monte Carlo Planning with Large Language Model for Text-Based Game Agentscited by 22
  12. 2022BR-SNIS: Bias Reduced Self-Normalized Importance Samplingcited by 12
8 more
  1. 2022Epistemic Monte Carlo Tree Searchcited by 7
  2. 2024Value Improved Actor Critic Algorithmscited by 6
  3. 2021Batch Monte Carlo Tree Searchcited by 5
  4. 2025Trust-Region Twisted Policy Improvementcited by 5
  5. 2020On Effective Parallelization of Monte Carlo Tree Searchcited by 4
  6. 2025Twice Sequential Monte Carlo for Tree Searchcited by 3
  7. 2019Multiple Policy Value Monte Carlo Tree Searchcited by 2
  8. 2025TransZero: Parallel Tree Expansion in MuZero using Transformer Networkscited by 1

Built on by

Not cited yet.