Technical Note: \cal Q-Learning
Machine Learning
Reinforcement learning with hidden states
Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
A unifying theorem for three subspace system identification algorithms
Automatica (Journal of IFAC) - Special issue on trends in system identification
Robot Learning
On Multiagent Q-Learning in a Semi-Competitive Domain
IJCAI '95 Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems
TCS Learning Classifier System Controller on a Real Robot
PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
Hi-index | 0.00 |
State space construction is one of the most fundamental issues for reinforcement learning methods to be applied to real robot tasks because they need a well-defined state space so that they can converge correctly. Especially in multi-agent environments, the problem becomes more difficult since visual information observed by a learning robot seems irrelevant to its self motion due to actions by other agents of which policies are unknown. This paper proposes a method which estimates the relationship between the learner's behaviors and the other agents' ones in the environment through interactions (observation and action) using the method of system identification to construct a state space in such an environment. In order to determine the state vectors of each agent. Akaike's Information Criterion is applied to the result of the system identification. Next, reinforcement learning based on the estimated state vectors is utilized to obtain the optimal behavior. The proposed method is applied to soccer playing physical agents, which learn to cope with a rolling ball and another moving agent. The computer simulations and the real experiments are shown and a discussion is given.