ikostrikov/pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
PythonMIT
Watchers
- aik7Brookhaven National Laboratory
- AjayTalatiLondon, UK
- andrewcz
- ArunkumarRamananAI Founder @Deep-Brainz & Stealth AI Labs
- berkeleymalagon
- chobaboInstitute of Agricultural Machinery, NARO
- dohnala@APITEA
- ethancaballero@mila-iqia
- fbrubacherMontevideo, Uruguay
- gandalfvn
- gych1824
- hasanalrasyidJapan
- ikostrikovUC Berkeley
- irustandiNew York metro
- jchassoul@spacebeam
- jhcloos
- justicelee
- kushalarora@mila-iqia @rllabmcgill
- marioycSonyAI
- MillionIntegralsMillion Integrals
- mmirmanExtensional
- nd1511Imperial College London, London, U.K.
- nomoreid
- paulovmdutra
- rigpalab
- rwightmanVancouver, BC
- santoshgskBengaluru, India
- scarlettDiMa
- smrutilTalentica
- strategist922Microsoft
- szagoruykoMTS AI
- ThanhL
- wookayinUniversity of Michigan
- wranai
- YuehChuanTaiwan
- zhuyiming