Login / Signup

Learn to Move Through a Combination of Policy Gradient Algorithms: DDPG, D4PG, and TD3.

Nicolas BachAndrew MelnikMalte SchillingTimo KorthalsHelge J. Ritter
Published in: LOD (2) (2020)
Keyphrases
  • learning algorithm
  • gradient ascent
  • reinforcement learning
  • computational complexity
  • worst case
  • optimization problems
  • machine learning algorithms
  • natural gradient