3 papers
cs.LG2022
World Value Functions: Knowledge Representation for Multitask Reinforcement Learning
Geraud Nangue Tasse, Steven James, Benjamin Rosman
An open problem in artificial intelligence is how to learn and represent knowledge that is sufficient for a general agent that needs to solve multiple tasks in a given world. In th…
cs.LG2021
Learning to Follow Language Instructions with Compositional Policies
Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan +3
We propose a framework that learns to execute natural language instructions in an environment consisting of goal-reaching tasks that share components of their task descriptions. Ou…
cs.LG2020
A Boolean Task Algebra for Reinforcement Learning
Geraud Nangue Tasse, Steven James, Benjamin Rosman
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 Bool…