Adversarially Guided Actor-Critic
ICLR 2021, 2021.
This paper introduced Adversarially Guided Actor-Critic, a modification to the traditional actor-critic framework: an adversary network is added to the policy gradient objective
Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments. These methods consider a policy (the actor) and a value (the critic) whose respective losses are obtained using different motivations and approaches. We introduce a third protagon...More
PPT (Upload PPT)