Login / Signup

Offline RL via Feature-Occupancy Gradient Ascent.

Gergely NeuNneka Okolo
Published in: CoRR (2024)
Keyphrases
  • gradient ascent
  • policy gradient
  • reinforcement learning
  • cross entropy
  • expectation maximization
  • exponential family
  • neural network
  • machine learning
  • multi agent
  • feature vectors