We study the problem of learning probabilistic models of high-level strategic behavior in the real-time strategy (RTS) game StarCraft. The models are automatically learned from sets of game logs and aim to capture the common strategic states and decision points that arise in those games. Unlike most work on behavior/strategy learning and prediction in RTS games, our data-centric approach is not biased by or limited to any set of preconceived strategic concepts. Further, since our behavior model is based on the well-developed and generic paradigm of hidden Markov models, it supports a variety of uses for the design of AI players and human assistants. For example, the learned models can be used to make probabilistic predictions of a player's future actions based on observations, to simulate possible future trajectories of a player, or to identify uncharacteristic or novel strategies in a game database. In addition, the learned qualitative structure of the model can be analyzed by humans in order to categorize common strategic elements. We demonstrate our approach by learning models from 331 expert-level games and provide both a qualitative and quantitative assessment of the learned model's utility.
Sample-based tree search (SBTS) is an approach to solving Markov decision problems based on constructing a lookahead search tree using random samples from a generative model of the MDP. It encompasses Monte Carlo tree search (MCTS) algorithms like UCT as well as algorithms such as sparse sampling. SBTS is well-suited to solving MDPs with large state spaces due to the relative insensitivity of SBTS algorithms to the size of the state space. The limiting factor in the performance of SBTS tends to be the exponential dependence of sample complexity on the depth of the search tree. The number of samples required to build a search tree is O((|A|B)^d), where |A| is the number of available actions, B is the number of possible random outcomes of taking an action, and d is the depth of the tree. State abstraction can be used to reduce B by aggregating random outcomes together into abstract states. Recent work has shown that abstract tree search often performs substantially better than tree search conducted in the ground state space. This paper presents a theoretical and empirical evaluation of tree search with both fixed and adaptive state abstractions. We derive a bound on regret due to state abstraction in tree search that decomposes abstraction error into three components arising from properties of the abstraction and the search algorithm. We describe versions of popular SBTS algorithms that use fixed state abstractions, and we introduce the Progressive Abstraction Refinement in Sparse Sampling (PARSS) algorithm, which adapts its abstraction during search. We evaluate PARSS as well as sparse sampling with fixed abstractions on 12 experimental problems, and find that PARSS outperforms search with a fixed abstraction and that search with even highly inaccurate fixed abstractions outperforms search without abstraction. These results establish progressive abstraction refinement as a promising basis for new tree search algorithms, and we propose directions for future work within the progressive refinement framework.
Monte Carlo tree search (MCTS) algorithms are a popular approach to online decision-making in Markov decision processes (MDPs). These algorithms can, however, perform poorly in MDPs with high stochastic branching factors. In this paper, we study state aggregation as a way of reducing stochastic branching in tree search. Prior work has studied formal properties of MDP state aggregation in the context of dynamic programming and reinforcement learning, but little attention has been paid to state aggregation in MCTS. Our main result is a performance loss bound for a class of value function-based state aggregation criteria in expectimax search trees. We also consider how to construct MCTS algorithms that operate in the abstract state space but require a simulator of the ground dynamics only. We find that trajectory sampling algorithms like UCT can be adapted easily, but that sparse sampling algorithms present difficulties. As a proof of concept, we experimentally confirm that state aggregation can improve the finite-sample performance of UCT.
-The iLOG Project (Intelligent LearningObject Guide) is designed to augment multimedia learning objects with information about (1) how a learning object has been used, (2) how it has impacted instruction and learning, and (3) how it should be used. The goal of the project is to generate metadata tags from data collected while students interact with learning objects; these metadata tags can then be used to help teachers identify learning objects that match the educational and experiential backgrounds of their students. The project involves the development of an agent-based intelligent system for tracking student interaction with learning objects, in tandem with an extensive learning research agenda. This paper provides an overview of this NSF-funded project, focusing on the instructional approach and research on varying levels of active learning and feedback. Using a randomized design and a hierarchical linear modeling framework, research showed that the active learning conditions resulted in significantly higher student learning. The elaborative feedback results approached (p = .056), but did not reach, the established significance criteria of alpha = .05. Both active learning conditions and one of the elaborative feedback conditions resulted in significantly higher content assessment scores compared to a control group.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.