actor critic model - Robuta Search

https://arxiv.org/abs/1710.11277 [1710.11277] Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning Abstract page for arXiv paper 1710.11277: Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning actor critic model https://openreview.net/forum?id=Skln2A4YDB Model-Augmented Actor-Critic: Backpropagating through Paths | OpenReview Policy gradient through backpropagation through time using learned models and Q-functions. SOTA results in reinforcement learning benchmark environments. actor critic model augmented paths openreview