Transcription of CONTINUOUS CONTROL WITH DEEP REINFORCEMENT …
{{id}} {{{paragraph}}}
Example: quiz answers
CONTINUOUS CONTROL WITH DEEP REINFORCEMENT …
Published as a conference paper at ICLR 2016 CONTINUOUS CONTROL WITH DEEP REINFORCEMENTLEARNINGT imothy P. Lillicrap , Jonathan J. Hunt , Alexander Pritzel, Nicolas Heess,Tom Erez, Yuval Tassa, David Silver & Daan WierstraGoogle DeepmindLondon, UK{countzero, jjhunt, apritzel, heess,etom, tassa, davidsilver, wierstra}@ adapt the ideas underlying the success of Deep Q-Learning to the continuousaction domain. We present an actor-critic, model-free algorithm based on the de-terministic policy gradient that can operate over CONTINUOUS action spaces. Usingthe same learning algorithm, network architecture and hyper-parameters, our al-gorithm robustly solves more than 20 simulated physics tasks, including classicproblems such as cartpole swing-up, dexterous manipulation, legged locomotionand car driving.
tasks, have continuous (real valued) and high dimensional action spaces. DQN cannot be straight-forwardly applied to continuous domains since it relies on a finding the action that maximizes the action-value function, which in the continuous valued case requires an iterative optimization process at every step.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: