Will's Papers
Title List
Complete List
- "Adversarial Reinforcement Learning."
Uther, W. T. B. and M. M. Veloso
Reinforcement Learning has been used for a number of years in single agent environments. This article reports on our investigation of Reinforcement Learning techniques in a multi-agent and adversarial environment with continuous observable state information. We introduce a new framework, two-player hexagonal grid soccer, in which to evaluate algorithms. We then compare the performance of several single-agent Reinforcement Learning techniques in that environment. These are further compared to a previously developed adversarial Reinforcement Learning algorithm designed for Markov games. Building upon these efforts, we introduce new algorithms to handle the multi-agent, the adversarial, and the continuous-valued aspects of the domain. We introduce a technique for modelling the opponent in an adversarial game. We introduce an extension to Prioritized Sweeping that allows generalization of learnt knowledge over neighboring states in the domain; and we introduce an extension to the U Tree generalizing algorithm that allows the handling of continuous state spaces. Extensive empirical evaluation is conducted in the grid soccer domain.
- Generalizing Adversarial Reinforcement Learning.
Uther, W. T. B. and M. M. Veloso
AAAI Fall Symposium on Model Directed Autonomous Systems, 1997.Reinforcement Learning has been used for a number of years in single agent environments. This article reports on our investigation of Reinforcement Learning techniques in a multi-agent and adversarial environment with continuous observable state information. Our framework for evaluating algorithms is two-player hexagonal grid soccer. We introduce an extension to Prioritized Sweeping that allows generalization of learnt knowledge over neighboring states in the domain and we introduce an extension to the U Tree generalizing algorithm that allows the handling of continuous state spaces.