The Termination Critic

Abstract

In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents. We propose an algorithm that focuses on the termination condition, as opposed to -- as is common -- the policy. The termination condition is usually trained to optimize a control objective: an option ought to terminate if another has better value. We offer a different, information-theoretic perspective, and propose that terminations should focus instead on the compressibility of the option's encoding -- arguably a key reason for using abstractions. To achieve this algorithmically, we leverage the classical options framework, and learn the option transition model as a "critic" for the termination condition. Using this model, we derive gradients that optimize the desired criteria. We show that the resulting options are non-trivial, intuitively meaningful, and useful for learning and planning.

AISTATS 2019

Cited by in corpus (6)

• Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
• TempoRL: Learning When to Act
• Discovery of Options via Meta-Learned Subgoals
• Temporally-Extended ε-Greedy Exploration
• LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
• Options of Interest: Temporal Abstraction with Interest Functions