Login / Signup

Exploiting Multiple Abstractions in Episodic RL via Reward Shaping.

Roberto CipolloneGiuseppe De GiacomoMarco FavoritoLuca IocchiFabio Patrizi
Published in: CoRR (2023)
Keyphrases
  • reinforcement learning
  • reward shaping
  • search algorithm
  • reinforcement learning algorithms
  • state space