This paper studies the impact of the initial data gathering method on the subsequent learning of a dynamics model. Dynamics models approximate the true transition function of a given task, in order to perform policy search directly on the model rather than on the costly real system. This study aims to determine how to bootstrap a model as efficiently as possible, by comparing initialization methods employed in two different policy search frameworks in the literature. The study focuses on the model performance under the episode-based framework of Evolutionary methods using probabilistic ensembles. Experimental results show that various task-dependant factors can be detrimental to each method, suggesting to explore hybrid approaches.

Multi-agent path finding has been proven to be a PSPACE-hard problem. Generating such a centralised multi-agent plan can be avoided, by allowing agents to plan their paths separately. However, this results in an increased number of collisions and agents must re- plan frequently. In this paper we present a framework for multi-agent path planning, which allows agents to plan independently and solve conflicts locally when they occur. The framework is a generalisation of the CQ-learning algorithm which learns sparse interactions between agents in a multi-agent reinforcement learning setting