In recent years, a reinforcement learning approach to build an agent's knowledge in a multi-agent world has prevailed when the reinforcement learning is applied to such a world, "a concurrent learning among the agents", "a perceptual aliasing", and "a designing rewards" are the most important problems to be considered. We have already confirmed that profit-sharing algorithm shows its robustness against these three problems through some experiments. In this paper, we focus on an advantage of profit-sharing compared to Q-learning through the simulations of controlling cranes where there exist the conflicts among the agents. The conflict resolution problem must become a bottle-neck in the multi-agent world if we approach to it by the top-down method. Similarly, Q-learning is also weak in this problem without exhaustive design of the rewards or detailed information about other agents. We present that profit-sharing method can be available to resolve it, through the results of some experiments on the controlling cranes problem.
[1]
Ming Tan,et al.
Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents
,
1997,
ICML.
[2]
Sandip Sen,et al.
Multiagent Coordination with Learning Classifier Systems
,
1995,
Adaption and Learning in Multi-Agent Systems.
[3]
R. James Firby,et al.
An Investigation into Reactive Planning in Complex Domains
,
1987,
AAAI.
[4]
Gerhard Weiss,et al.
Learning to Coordinate Actions in Multi-Agent-Systems
,
1993,
IJCAI.
[5]
Michael L. Littman,et al.
Markov Games as a Framework for Multi-Agent Reinforcement Learning
,
1994,
ICML.
[6]
Michael P. Wellman,et al.
Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
,
1998,
ICML.
[7]
Dana H. Ballard,et al.
Active Perception and Reinforcement Learning
,
1990,
Neural Computation.