2000 character limit reached
Solving Atari Games Using Fractals And Entropy (1807.01081v1)
Published 3 Jul 2018 in cs.AI
Abstract: In this paper, we introduce a novel MCTS based approach that is derived from the laws of the thermodynamics. The algorithm coined Fractal Monte Carlo (FMC), allows us to create an agent that takes intelligent actions in both continuous and discrete environments while providing control over every aspect of the agent behavior. Results show that FMC is several orders of magnitude more efficient than similar techniques, such as MCTS, in the Atari games tested.
Collections
Sign up for free to add this paper to one or more collections.