Learning to Observe with Reinforcement Learning

We consider a reinforcement learning (RL) framework where the RL agent learns to adjust the accuracy of the observations alongside learning to perform the original task. We are interested in revealing the information structure of the observation space illustrating which type of observations are the most important (such as position versus velocity) and the dependence of this on the state of agent (such as at the bottom versus top of a hill). We approach this problem by associating a cost with collecting observations which increases with the accuracy. In contrast to the existing work that mostly focuses on sample efficiency during training, our focus is on the behaviour of the agent during the actual task. Our results quantify how the RL agent can learn to use the observation space efficiently and obtain satisfactory performance in the original task while collecting effectively smaller amount of data.