Official implementation of the AAAI 2021 paper Deep Bayesian Quadrature Policy Optimization.
reinforcement-learning deep-learning monte-carlo deep-reinforcement-learning pytorch policy-gradient gaussian-processes continuous-control actor-critic mujoco trust-region-policy-optimization advantage-actor-critic roboschool probablistic-numerics bayesian-quadrature natural-policy-gradient
-
Updated
Feb 17, 2021 - Python