Machine Learning - Special issue on reinforcement learning
| Hi-index | 0.02 |
It is known that the complexity of the reinforcement learning algorithms, such as Q-learning, may be exponential in the number of environment's states. It was shown, however, that the learning complexity for the goal-directed problems may be substantially reduced by initializing the Q-values with a "good" approximative function. In the multiagent case, there exists such a good approximation for a big class of problems, namely, for goal-directed stochastic games. These games, for example, can reflect coordination and common interest problems of cooperative robotics. The approximative function for these games is nothing but the relaxed, single-agent, problem solution, which can easily be found by each agent individually. In this article, we show that (1) an optimal single-agent solution is a "good" approximation for the goal-directed stochastic games with action-penalty representation and (b) the complexity is reduced when the learning is initialized with this approximative function, as compared to the uninformed case.