rail-berkeley/softlearning
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
PythonNOASSERTION
Watchers
- athakapoCERTH, convcao group
- boostf
- Dr-Tuski
- eemailme
- errorer-max
- Fkeverything
- gxhrid
- hartikainenGoogle / DeepMind
- jhcloos
- jingh4t1qbit
- jrabaryCEA LIST
- jskDrTecAce
- justicelee
- kbichave
- KelvinsonSomewhere
- LelouchWuWgames
- manavchoudhary
- markovyao
- mktalMeta AI
- mysl
- nunofernandes-plightPhotonics Precision Technologies, The Intelligence of Information & FasterCapital
- pete21
- qingtian1771
- RedLeader962@norlab-ulaval
- shuvoxcd01Infolytx Bangladesh Limited
- srisadhanSan Francisco, CA
- strategist922Microsoft
- svlevine
- thatscotdatasci@PhysicsXLtd
- TMatsThe University of Tokyo @matsuolab @matsuolab-research
- TonyAbellSanta Monica
- wx-bRIOS
- ying-wenShanghai Jiao Tong University
- yotofu
- zhixuan-wei
- ZhuFengdaaaMonash University