is this an error：num_steps += (t + 1) ？

Khrylx / PyTorch-RL

PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.

MIT License

1.1k stars 188 forks source link

is this an error：num_steps += (t + 1) ？ #20

Closed pprivulet closed 4 years ago

pprivulet commented 4 years ago

Is this an error in file core/agent.py line 59: num_steps += (t + 1) ?

Khrylx commented 4 years ago

This is not as if the agent only takes one step, t is still 0