google-deepmind/ai-safety-gridworlds
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
PythonApache-2.0
Watchers
- akfidjelandDeepMind
- arhikHyderabad
- arunsathiya@automattic
- BertRaeymaekersBelgium
- davids91
- Flowy
- gabrielcc2Rewe Digital, University of Magdeburg, OvGU
- genf
- IanRiceDevErie, Pennsylvania
- IsminoulaSchool of Information Sciences, University of Illinois Urbana Champaign
- janleikeLondon, UK
- jared83
- jhcloos
- justicelee
- jvmncs@zed-industries
- laurencecaoShanghai
- levitationSimplify / Macrotec LLC
- MetaxalGoogle DeepMind
- Miguel-FuentesUniversity of Massachusetts Amherst
- miljanm@deepmind
- mr0re1Google
- nunofernandes-plightPhotonics Precision Technologies, The Intelligence of Information & FasterCapital
- pbliszko
- pierg
- pokaxpoka
- rafaelcastrocouto@spicylobstergames
- RatJugglerSmallfield, England
- rwill128Atlanta, GA
- Tamiks
- TheCDCSoftware Engineer at NAVSEA Corona
- thibaultcalvayrac
- UdoFrankfurt, Germany
- vepoblioVEPO
- VylkireNSW, AU
- wookayinUniversity of Michigan
- zawie@aws