rlcode/reinforcement-learning

Cartpole Policy Gradient script does not converge (2-cartpole/3-reinforce/cartpole_reinforce.py)

a-ozbek opened this issue · 0 comments

I am running the script here but even after 500 episodes it does not converge. You can see the graph I get below:
score

In contrast this is the supposedly converged graph from repo:
cartpole_reinforce

Can you please advise why this is the case? I did not change any parameters, just ran the script as it is.