National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Cooperation with Unknown Agents in Multi-agent Environment
Bašta, Přemysl ; Pilát, Martin (advisor) ; Straka, Milan (referee)
Over the past few decades, we have witnessed great successes in the field of deep and reinforcement learning. Great achievements have been made in many competitive settings, both in single-agent and multi-agent environments, where AI has managed to outperform human experts and even entire teams of human experts. However, the situation is much more difficult when cooperation is required in purely cooperative environments. We first give a brief overview of reinforcement learning theory and current state of the art algorithms. We then extend the theory to multi-agent systems, where several related issues are discussed. And finally, we propose novel approaches of agent training where we use a simplified multi-agent cooperative cooking game environment based on the popular game Overcooked, we attempt to train agents that are robust and capable of ad hoc agent cooperation.
Space game with artificial intelligence
Bašta, Přemysl ; Pilát, Martin (advisor) ; Gemrot, Jakub (referee)
Part of this thesis consists of the implementation of my own simple space game which serves as an experimenting en vironment for testing different aproaches of artificial inteligence. There have been created abstractions in a form of sensoric methods and action plans as a transition between low leve l and high level information about game state and actions. These abstractions help algorithms of artifical inteligence with game agent manipulation. As far as algorithms are considered I chose genetic programming and Deep Q-learning as main aproachces for inteli gent agent development. Final part contains description of behaviour of developed agents and discussion of performed experiments.

See also: similar author names
2 Bašta, Petr
Interested in being notified about new results for this query?
Subscribe to the RSS feed.