Will it Blend? Composing Value Functions in Reinforcement Learning

07/12/2018
by   Benjamin van Niekerk, et al.
0

An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a principled way. We provide a "recipe" for optimal value function composition in entropy-regularised reinforcement learning (RL) and then extend this to the standard RL setting. Composition is demonstrated in a video game environment, where an agent with an existing library of policies is able to solve new tasks without the need for further learning.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset