Causal State Distillation for Explainable Reinforcement Learning

arXiv:2401.00104v2 Announce Type: replace
Abstract: Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing problem, making it difficult for users to grasp the reasons behind an agent's behaviour. Various approaches have been explored to address this problem, with one promising avenue being reward decomposition (RD). RD is appealing as it sidesteps some of the concerns …

abstract agent agents arxiv causal cs.ai cs.lg decisions distillation intelligent making reinforcement reinforcement learning state stat.me training transparency type understanding