ARS

ARS copied to clipboard

Training on BipedalWalkerHardcore seems to result in a negative reward

1

Hi and thanks for sharing the code. I've tried to run the training process on a different environment such as the `BipedalWalkerHardcore-v2` but it seems that is not able to...

kirk86

While trying to run some examples to benchmark this code, I had to make a few small changes to work with ray 1.0, and to reflect that the mujoco 1.0...

sgillen

License - trained policies

2

Hi, We want to use trained policies data in Nevergrad for the purpose of benchmarking Mujoco envs. We thus add ARS license in the concerned folder and link your repository...

herilalaina

can you explain to me or maybe just give me some pointer about this. what should i do if i want to make the agent output some discrete action? thank...

adhityairvan

Fixed error of run_policy.py with python 3.6

1

Fixed error of run_policy.py with python 3.6, lin_policy.items() returns ItemsView in python 3.6, converting to list is not allowed, thus one can use `lin_policy.f.arr_0` or `lin_policy[lin_policy.files[0]]`.

kirk86

About SHIFT

1

I have no idea about why we need to subtract a shift from reward, and how to set this value?

yichaowa

Divide by zero

4

Hi, First and foremost, thanks for sharing the code. This is greatly appreciated. Currently testing ARS in other learning environments and found that for very difficult environments the users of...

pedronahum

Hello, thank you guys for this great code, I've been using it to my research. I wanted to know if there is some code for the Basic Random Search only.

abcp4