Daniel Seita

Your PyBullet vs Official PyBullet Implementations?

1

Hi @Zackory this is great work! I have been working closely with PyBullet over the last few months, and am using the official PyBullet code installed via `pip install pybullet==3.0.4`...

RuntimeError: module compiled against API version 0xe but this version of numpy is 0xd

3

I followed the three installation steps for my **Ubuntu 18.04 machine** to create a conda environment named `ravens`. The installation seems to have proceeded correctly. However, running the example shows...

DDPG implementation fails to learn well on at least five MuJoCo-v2 envs for all three noise types. I report steps to reproduce and learning curve plots [and show that PPO2 seems to work fine].

21

Dear @pzhokhov @matthiasplappert @christopherhesse et al., Thank you for providing an implementation of DDPG. However, I have been unable to get it to learn well on the standard MuJoCo environments...

Thanks for a great guide to debugging! I was using the assertions code you wrote. However, note that `tf.with_dependencies` is now deprecated and results in errors when used. The alternative,...

Some benchmarks on six MuJoCo-v2 environments for DDPG and TD3

3

Hi @vitchyr Thanks for the great code base. I was recently benchmarking some results here in search for some DDPG/TD3 implementations after [my failure to get baselines working](https://github.com/openai/baselines/issues/938). I thought...

How to adjust epsilon (in epsilon greedy) on a per-episode basis, in parallel?

7

Hi Adam, Thanks again for getting rlpyt set up. I am wondering if it is possible to do this when running RL in parallel: within each parallel environment, at the...

Because I should know how to fix the current bugs in my code. - [ ] DDPG - [ ] TRPO

Asynchronous Advantage Actor-Critic

2

I need that algorithm implemented here!!!

Let's leave Python 2.7 behind and make everything 3.5+ for this repository. If I need to go back to Python 2.7, make a virtualenv.

I need to make this code more modular and flexible, and take full advantage of Python's features. The policies right now are kind of hard-coded awkwardly. Look at `modular_rl` and...