> While it is possible to acquire a quasi-PI agent by training with randomly shuffled observations and hope the agent’s policy network has enough capacity to memorize all the patterns, we aim for a design that achieves true PI even if the agent is trained with fix-ordered observations.
> While it is possible to acquire a quasi-PI agent by training with randomly shuffled observations and hope the agent’s policy network has enough capacity to memorize all the patterns, we aim for a design that achieves true PI even if the agent is trained with fix-ordered observations.