paper-with-me

Papers

Convolutional Monte Carlo Rollouts in Go

2015-12-10 · Peter H. Jin, Kurt Keutzer

In this work, we present a MCTS-based Go-playing program which uses convolutional networks in all parts. Our method performs MCTS in batches, explores the Monte Carlo search tree using Thompson sampling and a convolutional network, and evaluates convnet-based rollouts on the GPU. We achieve strong win rates against open source Go programs and attain competitive results against state of the art convolutional net-based Go-playing programs.

📄 PDF Abstract BibTeX arXiv:1512.03375

Code (0)

등록된 구현이 없습니다.

Tasks

GPUThompson Sampling

Similar Papers 제목 키워드 기반

Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation

2019-12-31 · ICLR 2020 1 · Xinjie Fan, Yizhe Zhang, Zhendong Wang, Mingyuan Zhou

Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to conte…

Image CaptioningProgram SynthesisReinforcement Learning

Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control

2025-05-13 · Hazim Alzorgan, Abolfazl Razi

Actor-critic methods, like Twin Delayed Deep Deterministic Policy Gradient (TD3), depend on basic noise-based exploration, which can result in less than optimal policy convergence. In this study, we introduce Monte Carlo…

Computational Efficiencycontinuous-controlContinuous Control

Doubly Robust Monte Carlo Tree Search

2025-02-01 · Manqing Liu, Andrew L. Beam

We present Doubly Robust Monte Carlo Tree Search (DR-MCTS), a novel algorithm that integrates Doubly Robust (DR) off-policy estimation into Monte Carlo Tree Search (MCTS) to enhance sample efficiency and decision quality…

Decision Making

Better Computer Go Player with Neural Network and Long-term Prediction

2015-11-19 · Yuandong Tian, Yan Zhu

Competing with top human players in the ancient game of Go has been a long-term goal of artificial intelligence. Go's high branching factor makes traditional search techniques ineffective, even on leading-edge hardware, …

4kGame of Go

Tempered Sequential Monte Carlo for Trajectory and Policy Optimization with Differentiable Dynamics

2026-04-23 · Heng Yang arxiv

We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design as inference. Specifically, we minimize a KL-regularized expected tra…