Monte-Carlo Tree Search: A New Framework for Game AI

Chaslot, Guillaume; Bakkes, Sander; Szita, István; Spronck, Pieter

doi:10.1609/aiide.v4i1.18700

Cited by 122 publications

(51 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitively, extended environments can simulate the agent. This can be considered a dual version of AIs which simulate their environment, as in Monte Carlo Tree Search (Chaslot et al, 2008).…”

Section: Preliminariesmentioning

confidence: 99%

Extending Environments to Measure Self-reflection in Reinforcement Learning

Alexander

Castaneda²,

Compher

et al. 2022

Journal of Artificial General Intelligence

View full text Add to dashboard Cite

We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent’s hypothetical behavior. Since good performance usually requires paying attention to whatever things the environment’s outputs are based on, we argue that for an agent to achieve on-average good performance across many such extended environments, it is necessary for the agent to self-reflect. Thus weighted-average performance over the space of all suitably well-behaved extended environments could be considered a way of measuring how self-reflective an agent is. We give examples of extended environments and introduce a simple transformation which experimentally seems to increase some standard RL agents’ performance in a certain type of extended environment.

show abstract

Section: Preliminariesmentioning

confidence: 99%

Extending Environments to Measure Self-reflection in Reinforcement Learning

Alexander

Castaneda²,

Compher

et al. 2022

Journal of Artificial General Intelligence

View full text Add to dashboard Cite

show abstract

“…Several methods aim to improve the speed of the search such that decisions can be made quicker. They often use neural networks [35] and distributive computing [36,37] to achieve a linear speedup with a minimal performance drop. Liu et al [38] provide one such distributed approach called Watch the Unobserved Upper Confidence Trees (WU-UCT).…”

Section: Monte Carlo Tree Searchmentioning

confidence: 99%

Learning to Design Without Prior Data: Discovering Generalizable Design Strategies Using Deep Learning and Tree Search

Raina

Cagan

McComb

2022

Journal of Mechanical Design

View full text Add to dashboard Cite

Building an AI agent that can design on its own has been a goal since the 1980s. Recently, deep learning has shown the ability to learn from large-scale data, enabling significant advances in data-driven design. However, learning over prior data limits us only to solve problems that have been solved before and biases us towards existing solutions. The ultimate goal for a design agent is the ability to learn generalizable design behavior in a problem space without having seen it before. We introduce a self-learning agent framework in this work that achieves this goal. This framework integrates a deep policy network with a novel tree search algorithm, where the tree search explores the problem space, and the deep policy network leverages self-generated experience to guide the search further. This framework first demonstrates an ability to discover high-performing generative strategies without any prior data, and second, it illustrates a zero-shot generalization of generative strategies across various unseen boundary conditions. This work evaluates the effectiveness and versatility of the framework by solving multiple versions of two engineering design problems without retraining. Overall, this paper presents a methodology to self-learn high-performing and generalizable problem-solving behavior in an arbitrary problem space, circumventing the needs for expert data, existing solutions, and problem-specific learning.

show abstract

“…MCTS has been further employed in realtime games [Samothrakis, Robles, and Lucas, 2010] and Solitaire puzzles [Cazenave, 2007] where it can outperform humans. MCTS has also been used for other domains including optimization [Silver and Veness, 2010] and planning problems [Chaslot et al, 2008]. For more information, we refer reader to the excellent survey presented in [Browne et al, 2012].…”

Section: Monte Carlo Tree Searchmentioning

confidence: 99%

Generating Believable Stories in Large Domains

Kartal

Koenig

Guy

2021

AIIDE

View full text Add to dashboard Cite

Planning-based techniques are a very powerful tool for automated story generation. However, as the number of possible actions increases, traditional planning techniques suffer from a combinatorial explosion due to large branching factors. In this work, we apply Monte Carlo Tree Search (MCTS) techniques to generate stories in domains with large numbers of possible actions (100+). Our approach employs a Bayesian story evaluation method to guide the planning towards believable stories that reach a user defined goal. We generate stories in a novel domain with different type of story goals. Our approach shows an order of magnitude improvement in performance over traditional search techniques.

show abstract

Monte-Carlo Tree Search: A New Framework for Game AI

Cited by 122 publications

References 3 publications

Extending Environments to Measure Self-reflection in Reinforcement Learning

Extending Environments to Measure Self-reflection in Reinforcement Learning

Learning to Design Without Prior Data: Discovering Generalizable Design Strategies Using Deep Learning and Tree Search

Generating Believable Stories in Large Domains

Contact Info

Product

Resources

About