why tensorboardX's abscissa is not accurate?

sweetice / Deep-reinforcement-learning-with-pytorch

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

MIT License

3.75k stars 837 forks source link

Open xiaoxuh opened 5 years ago

xiaoxuh commented 5 years ago

tensorboard shows the episodes is 40k ,but in fact is140k