Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian.
Paria Rashidinejad, Hanlin Zhu, Kunhe Yang, Stuart Russell, Jiantao Jiao
Browse the full ICLR paper archive.
Paria Rashidinejad, Hanlin Zhu, Kunhe Yang, Stuart Russell, Jiantao Jiao
Browse the full ICLR paper archive.