Login / Signup

Dissecting Deep RL with High Update Ratios: Combatting Value Overestimation and Divergence.

Marcel HussingClaas VoelckerIgor GilitschenskiAmir-massoud FarahmandEric Eaton
Published in: CoRR (2024)
Keyphrases
  • reinforcement learning
  • multi agent
  • wide range
  • high precision
  • bayesian networks
  • state space
  • function approximation
  • deep learning