English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Building agents based on tree-search planning capabilities with learnedmodels has achieved remarkable success in classic decision-making problems,such as Go and Atari. However, it has been deemed challenging or eveninfeasible to extend Monte Carlo Tree Search (MCTS) based algorithms to diversereal-world applications, especially when these environments involve complexaction spaces and significant simulation costs, or inherent stochasticity. Inthis work, we introduce LightZero, the first unified benchmark for deployingMCTS/MuZero in general sequential decision scenarios. Specificially, wesummarize the most critical challenges in designing a general MCTS-styledecision-making solver, then decompose the tightly-coupled algorithm and systemdesign of tree-search RL methods into distinct sub-modules. By incorporatingmore appropriate exploration and optimization strategies, we can significantlyenhance these sub-modules and construct powerful LightZero agents to tackletasks across a wide range of domains, such as board games, Atari, MuJoCo,MiniGrid and GoBigger. Detailed benchmark results reveal the significantpotential of such methods in building scalable and efficient decisionintelligence. The code is available as part of OpenDILab athttps://github.com/opendilab/LightZero.

LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios