Realtime execution of automated plans using evolutionary robotics

Thompson, Tommy; Levine, John

doi:10.1109/cig.2009.5286456

Cited by 3 publications

(3 citation statements)

References 9 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LEBL is a learning technique devised to learn planning knowledge in two-player games, using incomplete explanations produced by considering only a subset of the set of possible actions or moves at each state during the expansion of the state space. Another example is the work in [283], which proposes an architecture combining the reasoning capabilities of classical planning (i.e., the ability to reason over long-term goals and devise plans to achieve them) with the reactive control capabilities of NNs (to execute those plans). Yet another example is the PEORL [225] framework, which proposes a methodology to address the problem of decision making in dynamic environments with uncertainty, based on the integration of symbolic planning, to guide the learning process, with hierarchical RL, to enrich symbolic knowledge and improve planning.…”

Section: Other Frameworkmentioning

confidence: 99%

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: Other Frameworkmentioning

confidence: 99%

A Survey of Planning and Learning in Games

et al. 2020

View full text Add to dashboard Cite

show abstract

“…However, the planning component is not connected to any real simulation. Thompson and Levine () compared the performance of an agent employing a classical planner on several runs in static and dynamic versions of the same environment. The article is, however, focused on the agent architecture and the performance comparison is very brief.…”

Section: Related Workmentioning

confidence: 99%

To Plan or to Simply React? An Experimental Study of Action Planning in a Game Environment

Černý

Barták

Brom

et al. 2015

Computational Intelligence

View full text Add to dashboard Cite

Many contemporary computer games, notably action and role‐playing games, represent an interesting class of navigation‐intensive dynamic real‐time simulations inhabited by autonomous intelligent virtual agents (IVAs). Although higher level reasoning of IVAs in these domains seems suited for action planning, planning is not widely adopted in existing games and similar applications. Moreover, statistically rigorous study measuring performance of planners in decision making in a game‐like domain is missing. Here, five classical planners were connected to the virtual environment of Unreal Development Kit along with a planner for delete‐free domains (only positive preconditions and positive effects). Performance of IVAs employing those planners and IVAs with reactive architecture was measured on a class of game‐inspired test environments of various sizes and under different levels of external interference. The analysis has shown that planning agents outperform reactive agents if (i) the size of the problem is small or if (b) the environment changes are either hostile to the agent or infrequent. In delete‐free domains, specialized approaches are inferior to classical planners because the lower expressivity of delete‐free domains results in lower plan quality. These results can help to determine when planning is advantageous in games and for IVAs control in other dynamic real‐time environments.

show abstract

“…However, the planning component is not connected to any real simulation. Thompson and Levine (2009) compared a performance of an agent employing a classical planner on several runs in static and dynamic versions of the same environment. The paper is however focused on the agent architecture and the performance comparison is very brief.…”

Section: Related Workmentioning

confidence: 99%

Planning and Reactive Agents in Dynamic Game Environments - An Experimental Study

Barták¹,

Brom²,

Černý³

et al. 2013

Proceedings of the 5th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

Many contemporary computer games can be described as dynamic real-time simulations inhabited by autonomous intelligent virtual agents (IVAs) where most of the environmental structure is immutable and navigating through the environment is one of the most common activities. Though controlling the behaviour of such agents seems perfectly suited for action planning techniques, planning is not widely adopted in existing games. This paper contributes to discussion whether the current academic planning technology is ready for integration to existing games and under which conditions. The paper compares reactive techniques to classical planning in handling the action selection problem for IVAs in game-like environments. Several existing classical planners that occupied top positions in the International Planning Competition were connected to the virtual environment of Unreal Development Kit via the Pogamut platform. Performance of IVAs employing those planners and IVAs with reactive architecture was measured on a class of gameinspired maze-like test environments under different levels of external interference. It was shown that agents employing classical planning techniques outperform reactive agents if the size of the planning problem is small or if the environment changes are either hostile to the agent or not very frequent.

show abstract

Realtime execution of automated plans using evolutionary robotics

Cited by 3 publications

References 9 publications

A Survey of Planning and Learning in Games

A Survey of Planning and Learning in Games

To Plan or to Simply React? An Experimental Study of Action Planning in a Game Environment

Planning and Reactive Agents in Dynamic Game Environments - An Experimental Study

Contact Info

Product

Resources

About