Related papers: Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning

Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning

URL: http://arxiv.org/abs/2207.11584v1
Date: Sat, 23 Jul 2022 19:23:29 GMT
Title: Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Authors: Michael Matthews, Mikayel Samvelyan, Jack Parker-Holder, Edward Grefenstette, Tim Rockt\"aschel
Abstract summary: Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. We investigate how skills can be incorporated into the training of reinforcement learning (RL) agents in complex environments. Our experiments show that learning with a prior knowledge of useful skills can significantly improve the performance of agents on complex problems.
Score: 27.69559938165733
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually trained end-to-end, with the hope being that useful skills will be implicitly learned in order to maximise discounted return of some extrinsic reward function. In this paper, we investigate how skills can be incorporated into the training of reinforcement learning (RL) agents in complex environments with large state-action spaces and sparse rewards. To this end, we created SkillHack, a benchmark of tasks and associated skills based on the game of NetHack. We evaluate a number of baselines on this benchmark, as well as our own novel skill-based method Hierarchical Kickstarting (HKS), which is shown to outperform all other evaluated methods. Our experiments show that learning with a prior knowledge of useful skills can significantly improve the performance of agents on complex problems. We ultimately argue that utilising predefined skills provides a useful inductive bias for RL problems, especially those with large state-action spaces and sparse rewards.