Reinforcement learning under incomplete perception using stochastic gradient ascent and recurrent neural networks

One of the important problems in reinforcement learning is the problem of incomplete perception, i.e., how to select the optimal action when the perception of the learning agent is not sufficient in detecting the states of the environment. One of the proposed solutions to this problem is to utilize recurrent neural networks for the architecture of the learning agent to build an internal dynamic model of the environment and to take actions based on the states of the model. Another approach is the stochastic gradient ascent method (SGA), proposed by Kimura et al. (1996), as a learning method for this problem. However, the SGA, which selects actions based on immediate percepts, can only achieve suboptimal performance under incomplete perception. This paper studies a combination of these techniques, where SGA is applied to recurrent neural networks. Computer simulations show that a learning agent using the proposed method can achieve optimal performance under incomplete perception.