ProMP: Proximal Meta-Policy Search.

Jonas Rothfuss Dennis Lee Ignasi Clavera Tamim Asfour Pieter Abbeel

Published in: ICLR (Poster) (2019)

Keyphrases

policy search
reinforcement learning
continuous state
reinforcement learning algorithms
dynamic programming
continuous action
partially observable markov decision processes
policy gradient
neural network
machine learning
bayesian networks
multi agent
state space
finite state
reward function