ProMP: Proximal Meta-Policy Search.

Jonas Rothfuss Dennis Lee Ignasi Clavera Tamim Asfour Pieter Abbeel

Published in: CoRR (2018)

Keyphrases

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