Deep Deterministic Policy Gradient

GPTKB entity

Statements (30)
Predicate Object
gptkbp:instanceOf reinforcement learning algorithm
gptkbp:abbreviation gptkb:DDPG
gptkbp:application autonomous vehicles
robotics
game playing
gptkbp:author gptkb:David_Silver
gptkb:Alexander_Pritzel
gptkb:Jonathan_J._Hunt
gptkb:Nicolas_Heess
gptkb:Tom_Erez
gptkb:Yuval_Tassa
gptkb:Timothy_P._Lillicrap
gptkb:Daan_Wierstra
gptkbp:basedOn actor-critic architecture
gptkbp:category model-free reinforcement learning
off-policy learning
gptkbp:developedBy gptkb:Google_DeepMind
gptkbp:handles continuous action spaces
https://www.w3.org/2000/01/rdf-schema#label Deep Deterministic Policy Gradient
gptkbp:inspiredBy gptkb:Q-learning
gptkbp:introducedIn 2015
gptkbp:publishedIn arXiv:1509.02971
gptkbp:relatedTo gptkb:Deep_Q-Network
Deterministic Policy Gradient
gptkbp:uses deep neural networks
experience replay
target networks
gptkbp:bfsParent gptkb:DDPG
gptkb:TD3
gptkbp:bfsLayer 7