Automated learning of hierarchical task networks for controlling minecraft agents

Nguyen, Chanh; Reifsnyder, Noah; Gopalakrishnan, Sriram; Muñoz-Ávila, Héctor

doi:10.1109/cig.2017.8080440

Cited by 7 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[152], RRT [200][201][202][203], BT [212,213] AGAI A* [150], RRT [198], CBP [206]. HTN [7,155,156], MCTS [169,170,174,176], (DP, RP) [189], EP [188] PF A* [148,149], RRT [197] MAC HTN [157,158], MCTS [166,167], PSP [191] NP HTN [161], TP [192], EP [193], INP [194] Overall, and as a conclusion, it can be said that planning has achieved significant success in game AI. Proof of this is the crucial role that planning has performed in achieving several milestones in AI research.…”

Section: Discussionmentioning

confidence: 99%

“…One such example concerns the problem of deriving agents that act in a more natural way. Examples of this include creating believable NPCs in serious games [7], generating characters with dynamic behavior in real-time video games [155], and deriving agents that can act has companions of the human player in Minecraft [156]. Other application Figure 6.…”

Section: Hierarchical Task Networkmentioning

confidence: 99%

“…and deriving agents that can act has companions of the human player in Minecraft [156]. Other application uses include tasks as diverse as strategic coordination of teams of agents [157,158], endowing agents with planning capabilities in fighting games [159], computing plans offline that can be used as game scripts [160], interactive storytelling using a model of personality traits [161], and macromanagement in RTS games [162].…”

Section: Hierarchical Task Networkmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Planning and Learning in Games

et al. 2020

View full text Add to dashboard Cite

In general, games pose interesting and complex problems for the implementation of intelligent agents and are a popular domain in the study of artificial intelligence. In fact, games have been at the center of some of the most well-known achievements in artificial intelligence. From classical board games such as chess, checkers, backgammon and Go, to video games such as Dota 2 and StarCraft II, artificial intelligence research has devised computer programs that can play at the level of a human master and even at a human world champion level. Planning and learning, two well-known and successful paradigms of artificial intelligence, have greatly contributed to these achievements. Although representing distinct approaches, planning and learning try to solve similar problems and share some similarities. They can even complement each other. This has led to research on methodologies to combine the strengths of both approaches to derive better solutions. This paper presents a survey of the multiple methodologies that have been proposed to integrate planning and learning in the context of games. In order to provide a richer contextualization, the paper also presents learning and planning techniques commonly used in games, both in terms of their theoretical foundations and applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Hierarchical Task Networkmentioning

confidence: 99%

Section: Hierarchical Task Networkmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Planning and Learning in Games

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Recent works have also considered learning abstractions for multi-level planning, like those in the task and motion planning (TAMP) [9,61] and hierarchical planning [62] literature. Some of these efforts consider learning symbolic action abstractions [34,63,64] or refinement strategies [18,20,65,66,67,68]; our operator and sampler learning methods take inspiration from these prior works. Recent efforts by Loula et al ( 2019) and Curtis et al ( 2021) consider learning both state and action abstractions for TAMP, like we do [16,17,69].…”

Section: Related Workmentioning

confidence: 99%

Inventing Relational State and Action Abstractions for Effective and Efficient Bilevel Planning

Silver¹,

Chitnis²,

Kumar³

et al. 2022

Preprint

View full text Add to dashboard Cite

Effective and efficient planning in continuous state and action spaces is fundamentally hard, even when the transition model is deterministic and known. One way to alleviate this challenge is to perform bilevel planning with abstractions, where a high-level search for abstract plans is used to guide planning in the original transition space. In this paper, we develop a novel framework for learning state and action abstractions that are explicitly optimized for both effective (successful) and efficient (fast) bilevel planning. Given demonstrations of tasks in an environment, our data-efficient approach learns relational, neuro-symbolic abstractions that generalize over object identities and numbers. The symbolic components resemble the STRIPS predicates and operators found in AI planning, and the neural components refine the abstractions into actions that can be executed in the environment. Experimentally, we show across four robotic planning environments that our learned abstractions are able to quickly solve held-out tasks of longer horizons than were seen in the demonstrations, and can even outperform the efficiency of abstractions that we manually specified. We also find that as the planner configuration varies, the learned abstractions adapt accordingly, indicating that our abstraction learning method is both "task-aware" and "planner-aware." Code: https://tinyurl.com/predicators-release

show abstract

“…Numeric conditions can be checked to see if numeric conditions in the actions are valid in the state. For example, in the minecraft domain, there is an action to build a pickaxe that requires three stones (Nguyen et al 2017). It can be checked directly in the state if the action is applicable.…”

Section: Immediate Expectationsmentioning

confidence: 99%

Is Everything Going According to Plan? Expectations in Goal Reasoning Agents

Muñoz-Ávila

Dannenhauer

Reifsnyder

2019

AAAI

Self Cite

View full text Add to dashboard Cite

In part motivated by topics such as agency safety, there is an increasing interest in goal reasoning, a form of agency where the agents formulate their own goals. One of the crucial aspects of goal reasoning agents is their ability to detect if the execution of their courses of actions meet their own expectations. We present a taxonomy of different forms of expectations as used by goal reasoning agents when monitoring their own execution. We summarize and contrast the current understanding of how to define and check expectations based on different knowledge sources used. We also identify gaps in our understanding of expectations.

show abstract

Automated learning of hierarchical task networks for controlling minecraft agents

Cited by 7 publications

References 4 publications

A Survey of Planning and Learning in Games

A Survey of Planning and Learning in Games

Inventing Relational State and Action Abstractions for Effective and Efficient Bilevel Planning

Is Everything Going According to Plan? Expectations in Goal Reasoning Agents

Contact Info

Product

Resources

About