google-deepmind/ai-safety-gridworlds
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
PythonApache-2.0
Stargazers
- 0xsuuUniversity of York
- andrewschreiberdozy.ai
- ardapekisStandard Model Biomedicine
- bwlambert
- bywbillySeattle, WA
- chris-chrisKorea
- danielegrattarola
- eyadsibai
- ffmpbgrnn
- fly51flyPRIS
- g-chang
- JackieTsengTsinghua University
- jsseely
- JunyoungJangKB Financial Group / KB Securities
- laurencecaoShanghai
- levitationSimplify / Macrotec LLC
- matteocng
- mavroudisvAlan Turing Institute
- Maxpridy@netmarble
- MetaxalGoogle DeepMind
- mraxilus
- n0p2
- nanxintinHuawei Noah's Ark Lab
- NataliaDiazUniversity of Granada, Spain
- rhythm92Japan
- samuelleachLondon, UK
- SeekPoint
- SeverTopan
- sighingnow@alibaba
- SimonTheCoderLiaoning, China
- stes@dynamical-inference @ki-macht-schule @kinematik-ai
- surajx@socialtrait
- theGreenJediLos Angeles
- tigerneilCenter for Safe AGI
- w1kkeDataUnion.app
- wwxFromTjuDRL/MAS