Login / Signup

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing.

Vint LeePieter AbbeelYoungwoon Lee
Published in: CoRR (2023)
Keyphrases
  • model based reinforcement learning
  • reinforcement learning
  • markov decision processes
  • machine learning
  • relational databases
  • collaborative filtering
  • maximum likelihood
  • long run
  • reward function