Login / Signup

Combining Deep Deterministic Policy Gradient with Cross-Entropy Method.

Tung-Yi LaiChu-Hsuan HsuehYou-Hsuan LinYeong-Jia Roger ChuBo Yang HsuehI-Chen Wu
Published in: TAAI (2019)
Keyphrases
  • cross entropy
  • gradient ascent
  • maximum likelihood
  • energy function
  • active learning
  • information retrieval
  • objective function
  • probabilistic model
  • error function