monoelh/deep-reinforcement-learning_DDQN_PPO_HER
MLP-framework (pure numpy) and DDQN-framework for OpenAI's Gym games. +test code for PPO added. +Hindsight Experience Replay(HER) bitflip-DQN example. +prioritized replay.
Jupyter Notebook
Stargazers
- AlexanderNahr
- arghyadeep99Barclays PLC
- binderwang
- haibaoliu
- jblewdvChicago, IL
- JerryIshiharaUC Berkeley
- juliusHuelsmannBerlin
- kitkitkit745
- knarxi
- liuyuezhangUT Austin
- ltbd78
- luckywlj
- maltehiBerlin, Germany
- Near32
- Plmono
- rishistypingParis, FR
- Smit1400Boston
- snknitin@WalmartLabs @iesl @Oracle @IBM @UMassAmherst
- vis4lan
- Weiyi-Zhang258