Making Reinforcement Learning Work on Swimmer.

Maël Franceschetti Coline Lacoux Ryan Ohouens Antonin Raffin Olivier Sigaud

Published in: CoRR (2022)

Keyphrases

reinforcement learning
state space
learning algorithm
function approximation
multi agent
markov decision processes
database
information systems
knowledge base
learning process
control system
optimal policy
action selection
relational reinforcement learning