Monte-Carlo Tree Search

Reinforcement LearningIntroduced 2006166 papers

Description

Monte-Carlo Tree Search is a planning algorithm that accumulates value estimates obtained from Monte Carlo simulations in order to successively direct simulations towards more highly-rewarded trajectories. We execute MCTS after encountering each new state to select an agent's action for that state: it is executed again to select the action for the next state. Each execution is an iterative process that simulates many trajectories starting from the current state to the terminal state. The core idea is to successively focus multiple simulations starting at the current state by extending the initial portions of trajectories that have received high evaluations from earlier simulations.

Source: Sutton and Barto, Reinforcement Learning (2nd Edition)

Image Credit: Chaslot et al

Papers Using This Method

VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents2025-06-17Calibrated Value-Aware Model Learning with Stochastic Environment Models2025-05-28Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning2025-05-21Adaptive Stress Testing Black-Box LLM Planners2025-05-08Adaptive Branch-and-Bound Tree Exploration for Neural Network Verification2025-05-02Trans-Zero: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data2025-04-20Neural-Guided Equation Discovery2025-03-21A Neural Symbolic Model for Space Physics2025-03-11OptionZero: Planning with Learned Options2025-02-23Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation2025-02-18Reinforcement Learning in Strategy-Based and Atari Games: A Review of Google DeepMinds Innovations2025-02-14Evaluating World Models with LLM for Decision Making2024-11-13Evaluating Robustness of Reinforcement Learning Algorithms for Autonomous Shipping2024-11-07Interpreting the Learned Model in MuZero Planning2024-11-07Human-aligned Chess with a Bit of Search2024-10-04Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models2024-09-28An Efficient and Generalizable Symbolic Regression Method for Time Series Analysis2024-09-06DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search2024-08-15Combining AI Control Systems and Human Decision Support via Robustness and Criticality2024-07-03Enhancements for Real-Time Monte-Carlo Tree Search in General Video Game Playing2024-07-03