An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments. (arXiv:1512.05509v1 [cs.NE])

This paper explores the performance of fitted neural Q iteration for reinforcement learning in several partially observable environments, using three recurrent neural network architectures: Long Short-Term Memory, Gated Recurrent Unit and MUT1, a recurrent neural architecture evolved from a pool of several thousands candidate architectures. A variant of fitted Q iteration, based on Advantage values instead of Q values, is also explored. The results show that GRU performs significantly better than LSTM and MUT1 for most of the problems considered, requiring less training episodes and less CPU time before learning a very good policy. Advantage learning also tends to produce better results.

Donate to arXiv

from cs.AI updates on arXiv.org http://ift.tt/1T4UGFt
via IFTTT