Login / Signup
The problem with DDPG: understanding failures in deterministic environments with sparse rewards.
Guillaume Matheron
Nicolas Perrin
Olivier Sigaud
Published in:
CoRR (2019)
Keyphrases
</>
reinforcement learning
database
genetic algorithm
high dimensional
sparse representation
markov decision processes
sparse coding
highly dynamic
learning algorithm
database systems
robotic systems
sparse data
canonical correlation analysis