Abstract— Decision trees, being human readable and hierarchically structured, provide a suitable mean to derive state-space abstraction and simplify the inclusion of the available knowledge for a Reinforcement Learning (RL) agent. In this paper, we address two approaches to combine and purify the available knowledge bstraction trees, stored among different RL agents in a multi-agent system, or among the decision trees learned by the same agent using different methods. Simulation results in nondeterministic football learning task provide strong evidences for enhancement in convergence rate and policy performance.