Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models.

Wenhao Ding Tong Che Ding Zhao Marco Pavone

Published in: ICML (2023)

Keyphrases

reinforcement learning
function approximation
multi agent
machine learning
bayesian models
neural network
dynamic programming
model selection
experimental data
dynamical systems
posterior probability
optimal control
learning capabilities
statistical inference
prior probabilities