A Boolean Task Algebra for Reinforcement Learning

01/06/2020
by   Geraud Nangue Tasse, et al.
38

We propose a framework for defining a Boolean algebra over the space of tasks. 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.

READ FULL TEXT

page 6

page 8

page 16

page 17

research
10/09/2021

Learning to Follow Language Instructions with Compositional Policies

We propose a framework that learns to execute natural language instructi...
research
07/12/2018

Will it Blend? Composing Value Functions in Reinforcement Learning

An important property for lifelong-learning agents is the ability to com...
research
05/18/2022

World Value Functions: Knowledge Representation for Multitask Reinforcement Learning

An open problem in artificial intelligence is how to learn and represent...
research
06/20/2023

BASS: Boolean Automorphisms Signature Scheme

We offer a digital signature scheme using Boolean automorphisms of a mul...
research
05/25/2022

Skill Machines: Temporal Logic Composition in Reinforcement Learning

A major challenge in reinforcement learning is specifying tasks in a man...
research
01/22/2019

Partial Order on the set of Boolean Regulatory Functions

Logical models have been successfully used to describe regulatory and si...
research
06/01/2020

Data-Driven Learning of Boolean Networks and Functions by Optimal Causation Entropy Principle (BoCSE)

Boolean functions and networks are commonly used in the modeling and ana...

Please sign up or login with your details

Forgot password? Click here to reset