Blind Decision Making: Reinforcement Learning with Delayed Observations

TL;DR

This paper introduces a reinforcement learning method that effectively handles delayed state observations without enlarging the state space, leading to improved decision-making when current state information is unavailable.

Contribution

The paper proposes a novel RL algorithm that manages delayed state updates without increasing the state space, enhancing performance in environments with observation delays.

Findings

Improved performance in RL environments with delayed observations

No increase in state space complexity

Faster convergence compared to traditional methods

Abstract

Reinforcement learning typically assumes that the state update from the previous actions happens instantaneously, and thus can be used for making future decisions. However, this may not always be true. When the state update is not available, the decision taken is partly in the blind since it cannot rely on the current state information. This paper proposes an approach, where the delay in the knowledge of the state can be used, and the decisions are made based on the available information which may not include the current state information. One approach could be to include the actions after the last-known state as a part of the state information, however, that leads to an increased state-space making the problem complex and slower in convergence. The proposed algorithm gives an alternate approach where the state space is not enlarged, as compared to the case when there is no delay in the state update. Evaluations on the basic RL environments further illustrate the improved performance of the proposed algorithm.