Fig. 1
From: Continual deep reinforcement learning with task-agnostic policy distillation
Illustration of the meta-environment, representing different game environments as tasks within the context of Atari 2600 games.
Fig. 1 | Scientific Reports
From: Continual deep reinforcement learning with task-agnostic policy distillation
Illustration of the meta-environment, representing different game environments as tasks within the context of Atari 2600 games.
