Variational Recurrent Models for Solving Partially Observable Control Tasks
This work addresses performance issues in partially observable environments for reinforcement learning agents, particularly in robotic control, but it appears incremental as it builds on existing methods.
The paper tackles the problem of poor performance in partially observable deep reinforcement learning tasks by proposing a variational recurrent model combined with an RL controller, achieving better data efficiency and more optimal policies in robotic control tasks where unobserved states are not easily inferred.
In partially observable (PO) environments, deep reinforcement learning (RL) agents often suffer from unsatisfactory performance, since two problems need to be tackled together: how to extract information from the raw observations to solve the task, and how to improve the policy. In this study, we propose an RL algorithm for solving PO tasks. Our method comprises two parts: a variational recurrent model (VRM) for modeling the environment, and an RL controller that has access to both the environment and the VRM. The proposed algorithm was tested in two types of PO robotic control tasks, those in which either coordinates or velocities were not observable and those that require long-term memorization. Our experiments show that the proposed algorithm achieved better data efficiency and/or learned more optimal policy than other alternative approaches in tasks in which unobserved states cannot be inferred from raw observations in a simple manner.