Self-Supervised Adversarial Imitation Learning. (arXiv:2304.10914v1 [cs.LG])

Behavioural cloning is an imitation learning technique that teaches an agent
how to behave via expert demonstrations. Recent approaches use self-supervision
of fully-observable unlabelled snapshots of the states to decode state pairs
into actions. However, the iterative learning scheme employed by these
techniques is prone to get trapped into bad local minima. Previous work uses
goal-aware strategies to solve this issue. However, this requires manual
intervention to verify whether an agent has reached its goal. We address this
limitation by …

advantages arxiv cloning decode expert framework imitation learning iterative observable state strategies supervision verify work