A Boolean Task Algebra for Reinforcement Learning

Abstract

The ability to compose learned skills to solve new tasks is an important property of lifelong-learning agents. In this work, we formalise the logical composition of tasks as a Boolean algebra. This allows us to formulate new tasks in terms of the negation, disjunction and conjunction of a set of base tasks. We then show that by learning goal-oriented value functions and restricting the transition dynamics of the tasks, an agent can solve these new tasks with no further learning. We prove that by composing these value functions in specific ways, we immediately recover the optimal policies for all tasks expressible under the Boolean algebra. We verify our approach in two domains---including a high-dimensional video game environment requiring function approximation---where an agent first learns a set of base skills, and then composes them to solve a super-exponential number of new tasks.

arXiv commentAccepted to the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada

References in corpus (4)

• Continuous control with deep reinforcement learning
• Learning to Navigate in Complex Environments
• Hindsight Experience Replay
• Composing Entropic Policies using Divergence Correction

Cited by in corpus (4)

• Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes
• Goal Kernel Planning: Linearly-Solvable Non-Markovian Policies for Logical Tasks with Goal-Conditioned Options
• Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines
• Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management