Login / Signup
Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration
Tingting Zhao
Hirotaka Hachiya
Voot Tangkaratt
Jun Morimoto
Masashi Sugiyama
Published in:
CoRR (2013)
Keyphrases
</>
lightweight
optimal policy
databases
action selection
expert systems
artificial neural networks
state space
computationally efficient
sample size