000			01697naa a2200193 4500
008			160926b xxu||||| |||| 00| 0 eng d
100			_aYogeswaran, Mohan
245			_aReinforcement Learning: Exploration - Exploitation Dilema in Multi Agent Foraging Task
260			_a _b _c
300			_a49 (3) Jul-Sep 2012, 223-236p.
520			_aThe exploration–exploitation dilemma has been an unresolved issue within the framework of multi-agent reinforcement learning. The agents have to explore in order to improve the state which potentially yields higher rewards in the future or exploit the state that yields the highest reward based on the existing knowledge. Pure exploration degrades the agent’s learning but increases the flexibility of the agent to adapt in a dynamic environment. On the other hand pure exploitation drives the agent’s learning process to locally optimal solutions. Various learning policies have been studied to address this issue. This paper presents critical experimental results on a number of learning policies reported in the open literatures. Learning policies namely greedy, ξ-greedy, Boltzmann Distribution (BD), Simulated Annealing (SA), Probability Matching (PM) and Optimistic Initial Values (OIV) are implemented to study on their performances on a multi-agent foraging-task modelled. Based on the numerical results that were obtained, the performances of the learning policies are discussed.
650			_aReinforcement
650			_aQ Learnign
650			_aLearning Policies
700			_aExploration - Exploitation Dilema
773	0		_d _oB-2508 _tBV- Opsearch (Jan - Dec 2012)
906			_aGeneral Management
942			_2ddc _c8
999			_c90357 _d90357