The State of Sparse Training in Deep Reinforcement Learning.
Laura GraesserUtku EvciErich ElsenPablo Samuel CastroPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- state space
- machine learning
- action space
- training phase
- function approximation
- supervised learning
- training algorithm
- dynamic programming
- data sets
- optimal policy
- markov decision processes
- learning process
- high dimensional
- multi agent
- learning agent
- training data
- hidden state
- avoid overfitting