-
Thanks for your great work. I find this environment very useful for our research. When I tried the training example, I got EOFError whenever the num-processes > 1. The error happens when the training …
-
Hello,I use your program and run 2000 episodes,but compare with your reslut , my reward didn't have the same obvious effect. The reward variation tendency didn't rise. I don't change the code, just se…
-
Hi Max,
this is the Dueling DQN implementation from DeepMind: https://arxiv.org/pdf/1511.06581.pdf
![image](https://user-images.githubusercontent.com/23219722/58774004-7d43f780-858d-11e9-8dc8-7b…
-
I am trying to use a trained model to predict on new data. The problem is that when I use multiple cpu's (12) I get a matrix of actions instead of one row: I get a row for every process spawned. Do I …
-
I'm going to take care of this. I made a separate branch to deal with it: dev_schrum_ppo
The goal is to make sure that we didn't break PPO by moving it into this code base.
-
Really cool that you've been working on implementing that algorithm in Python. I've been thinking of doing this as well. As far as I can tell, you're the only one that's tried doing this yet, so I'm …
-
Why cant OpenAI/GYM use something free? There are no other free physics engine that can be used? Im not a student and I dont have 500$ to pay for Mujoco every year. This is such a disappointment.
-
I recently read the paper [Time Limits in Reinforcement Learning](https://arxiv.org/abs/1712.00378), where the authors discuss what are the correct ways of dealing with time limits in reinforcement le…
-
Hi everyone,
As i noticed in the last version of GYM board games have been removed. Can you please inform me where i to find the last board games of GYM?, such the Go etc. Or is there any library t…
-
Hello,
I've been experimenting with the PPO2 algorithm using DummyVecEnv where the number of environments is set to 16. I've realized that in the learn method set_global_seeds use a single seed for e…
ecada updated
5 years ago