Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
This addresses the problem of enhancing AI agents' performance in text-based games for researchers in reinforcement learning and natural language processing, though it appears incremental as it applies an existing knowledge source to a known approach.
The paper tackles the challenge of improving reinforcement learning agents in text-based environments by incorporating commonsense knowledge from ConceptNet, resulting in promising performance on two such environments.
In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments. This reliance on text brings advances in natural language processing into the ambit of these agents, with a recurring thread being the use of external knowledge to mimic and better human-level performance. We present one such instantiation of agents that use commonsense knowledge from ConceptNet to show promising performance on two text-based environments.