pytorch-rl

pytorch-rl copied to clipboard

Hello! I've been learning how to code RL form your repo. I've replace duplicating code lines from def train def update_policy to agent's method self.sample_action(). And it seems that agent...

lemikhovalex

Hi Ben Thanks for the interesting notebooks. Upon studying the "3 - Advantage Actor Critic (A2C) [CartPole].ipynb" notebook, I came to the conclusion that detaching the returns in the update_policy()...

nimrare

actor critic possible error

2

Hello, Ben! Thank you for a great tutorial series. I have a question regarding your [actor-critic notebook](https://github.com/bentrevett/pytorch-rl/blob/master/2%20-%20Actor%20Critic%20%5BCartPole%5D.ipynb). In function `update_policy` ```python def update_policy(returns, log_prob_actions, values, optimizer): returns = returns.detach() policy_loss...

hawkeoni

Taking 'done' into consideration while calculating returns

1

Hello, thank you for making this repo, I think while calculating the returns you should take done into consideration as, ``` def calculate_returns(self, rewards, dones, normalize = True): returns =...

murtazabasu