A Closer Look at Deep Policy Gradients.
Andrew IlyasLogan EngstromShibani SanturkarDimitris TsiprasFirdaus JanoosLarry RudolphAleksander MadryPublished in: ICLR (2020)
Keyphrases
- optimal policy
- policy making
- data mining
- decision making
- e learning
- clustering algorithm
- case study
- database systems
- optimal solution
- information technology
- artificial neural networks
- probabilistic model
- state space
- artificial intelligence
- action selection
- image gradient
- asymptotically optimal
- deep learning
- real world