msinto93/T-REX-IRL
Trajectory-ranked Reward EXtrapolation (T-REX) for Inverse Reinforcement Learning - A Tensorflow implementation trained on OpenAI Gym environments
正在读取项目信息…
开源雷达国内 GitHub 镜像站
加速通道已就绪
返回列表
开源雷达国内 GitHub 镜像站
Trajectory-ranked Reward EXtrapolation (T-REX) for Inverse Reinforcement Learning - A Tensorflow implementation trained on OpenAI Gym environments