Team-Partitioned, Opaque-Transition Reinforcement Learning (1999)
Peter Stone and Manuela Veloso
We present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the use of action-dependent features to generalize the state space. In our work, we use a it learned action-dependent feature space to aid higher-level reinforcement learning. TPOT-RL is an effective technique to allow a team of agents to learn to cooperate towards the achievement of a specific goal. It is an adaptation of traditional RL methods that is applicable in complex, non-Markovian, multi-agent domains with large state spaces and limited training opportunities. TPOT-RL is fully implemented and has been tested in the robotic soccer domain, a complex, multi-agent framework. This paper presents the algorithmic details of TPOT-RL as well as empirical results demonstrating the effectiveness of the developed multi-agent learning approach with learned features.
In RoboCup-98: Robot Soccer World Cup II, Minoru Asada and Hiroaki Kitano (Eds.), Vol. 1604, pp. 261-72, Berlin 1999. Springer Verlag. Also in Proceedings of the Third International Conference on Autonomous Agents, 1999.

Peter Stone Faculty pstone [at] cs utexas edu