Keyframe Demonstration Seeded and Bayesian Optimized Policy Search.

Onur Berk Töre Farzin Negahbani Baris Akgün

Published in: CoRR (2023)

Keyphrases

policy search
reinforcement learning
continuous state
reinforcement learning algorithms
bayesian networks
dynamic programming
neural network
markov decision problems
monte carlo methods
state space
continuous action
control system
optimal policy
markov decision processes
reward function
policy gradient