Abstract
We study the problem of identifying the policy space available to an agent in a learning process, having access to a set of demonstrations generated by the agent playing the optimal policy in the considered space. We introduce an approach based on frequentist statistical testing to identify the set of policy parameters that the agent can control, within a larger parametric policy space. After presenting two identification rules (combinatorial and simplified), applicable under different assumptions on the policy space, we provide a probabilistic analysis of the simplified one in the case of linear policies belonging to the exponential family. To improve the performance of our identification rules, we make use of the recently introduced framework of the Configurable Markov Decision Processes, exploiting the opportunity of configuring the environment to induce the agent to reveal which parameters it can control. Finally, we provide an empirical evaluation, on both discrete and continuous domains, to prove the effectiveness of our identification rules.
Highlights
Reinforcement Learning (RL, Sutton and Barto, 2018) deals with sequential decision– making problems in which an artificial agent interacts with an environment by sensing perceptions and performing actions
We study the problem of identifying the policy space available to an agent in a learning process, having access to a set of demonstrations generated by the agent playing the optimal policy in the considered space
Additional experiments together with the hyperparameter values are reported in Appendix C. 6.1 Identification rules experiments we provide two experiments to test the ability of our identification rules in properly selecting the parameters the agent controls in different settings
Summary
Reinforcement Learning (RL, Sutton and Barto, 2018) deals with sequential decision– making problems in which an artificial agent interacts with an environment by sensing perceptions and performing actions. The agent’s goal is to find an optimal policy, i.e., a prescription of actions that maximizes the (possibly discounted) cumulative reward collected during its interaction with the environment. Machine Learning ability to map observations to actions. These three elements define the policy space available to the agent in the learning process. Agents having access to different policy spaces may exhibit different optimal behaviors, even in the same environment. The notion of optimality is necessarily connected to the space of policies the agent can access, which we will call the agent’s policy space in the following. The need to limit the policy space naturally emerges in many industrial applications, where some behaviors have to be avoided for safety reasons
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have