Haoyu Huang

icon indicating a website link https://blog.csdn.net/hhy_csdn

icon company Tsinghua University icon location Beijing, China icon location A Ph.D student of Center for Brain Inspired Computing Research, Tsinghua University, Beijing, China

Results 3 comments of Haoyu Huang

I dont think PPO pendulum is converging

I don't think this repo implement the PPO correctly either

Bugs in PPO

@yuntao-ma for index in BatchSampler(SubsetRandomSampler(range(self.buffer_capacity)), self.batch_size, True):

Benchmark :Test accuracy: 0.9682

more detail,please?