Semi-Supervised Off Policy Reinforcement Learning

no code implementations • 9 Dec 2020 • Aaron Sonabend-W, Nilanjana Laha, Ashwin N. Ananthakrishnan, Tianxi Cai, Rajarshi Mukherjee

2) The surrogate variables we leverage in the modified SSL framework are predictive of the outcome but not informative to the optimal policy or value function.

Imputation Q-Learning +2