search

rlcode / reinforcement-learning

Minimal and Clean Reinforcement Learning Examples
MIT License
3.35k stars 725 forks source link

Cartpole Policy Gradient script does not converge (2-cartpole/3-reinforce/cartpole_reinforce.py) #108

Open a-ozbek opened 3 years ago

a-ozbek commented 3 years ago

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.