Towards a Reinforcement Learning Module for Navigation in Video Games

Thierry Gourdin (1) , Olivier Sigaud (1)

1 Animatlab

Large real-world Probabilistic Temporal Planning (PTP) is a very challenging research field. A common approach is to model such problems as Markov Decision Problems (MDP) and use dynamic programming techniques. Yet, two major difficulties arise: 1- dynamic programming does not scale with the number of tasks, and 2- the probabilistic model may be uncertain, leading to the choice of unsafe policies. We build here on the Factored Policy Gradient (FPG) algorithm and on robust decision-making to address both difficulties through an algorithm that trains two competing teams of learning agents. As the learning is simultaneous, each agent is facing a non-stationary environment. The goal is for them to find a common Nash equilibrium.

Domaines: Informatique [cs]

Thierry Gourdin, Olivier Sigaud. Towards a Reinforcement Learning Module for Navigation in Video Games. ECML 2005 Workshop on Reinforcement Learning in Non-Stationary Environments, Oct 2005, Porto, Portugal. pp.1-12. ⟨hal-01491687⟩