Information asymmetry in KL-regularized RL.
Alexandre GalashovSiddhant M. JayakumarLeonard HasencleverDhruva TirumalaJonathan SchwarzGuillaume DesjardinsWojciech M. CzarneckiYee Whye TehRazvan PascanuNicolas HeessPublished in: ICLR (Poster) (2019)
Keyphrases
- information asymmetry
- reinforcement learning
- kullback leibler distance
- model free
- reinforcement learning algorithms
- function approximation
- risk minimization
- markov decision processes
- optimal policy
- least squares
- regularized least squares
- kullback leibler
- multi agent
- machine learning
- action selection
- state space
- markov chain
- supply chain
- cross entropy
- action space
- bayesian networks
- learning algorithm