louiskirsch/metagenrl
MetaGenRL, a novel meta reinforcement learning algorithm. Unlike prior work, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training.
Python
Stargazers
- 4SkyNet
- albzni
- alok-binaryWMF6+3G Cyberjaya, Selangor
- Athene-aiUnited Kingdom
- cinneesolMelbourne
- cvanoortUniversity of Vermont
- fly51flyPRIS
- GeorgeDUT
- hakanfireAnkara, Turkey
- IraKorshunovaGhent, Belgium
- jinyeom@microsoft
- jyericlinUniversity of Toronto
- kli-casiaCASIA
- LLT1Institute of Automation,Chinese Academy of Sciences
- madsurgeonUniversity of Zurich
- makdoudNPalaiseau, France
- manavchoudhary
- MasterScratSwitzerland
- n00b3rpwn4g3
- najibchy
- only-changerSJTU
- panamantisPanamantis Inc.
- penniepeng321Beijing
- philip-huangPittsburgh, USA
- R-Ceph
- schneimoRobert Bosch GmbH
- seba-1511Google DeepMind
- shichaosuper
- sjoerdvansteenkisteGoogle Research
- StaminaTang
- SunwardTreeWuhan, China
- Takonan
- tominku
- vijpandaturtleAmrita Vishwa Vidyapeetham
- w-hc
- zoeyuchaoTsinghua University