-
The rainbow agent by default experienced the best base result in sonic for the OpenAI team by a large margin, if you exclude the ridiculously resource intensive parallel PPO training:
https://arxiv…
-
Is this extendable for policy gradient or actor-critic architectures? Or would one have to do major re-workings? I'm trying to decide whether to use this framework for a project or implement from scra…
-
Getting this
error
```python
Traceback (most recent call last):
File "/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call
return fn(*a…
-
```python
from typing import List
from magenta.protobuf.music_pb2 import NoteSequence
from utils import save_midi, save_plot
def sample(model_name: str,
num_steps_per_sample: i…
-
### 1. What I did:
I'm trying to train Breakout on google colab using the A3C implementation. Whenever I run
`!python train-atari.py --env Breakout-v0 --gpu 0`
It causes an error;
Traceback…
-
Hi there! I really like the motivation behind this project, and have already shared it with some colleagues in the biology field. One question though - I import the notebooks into my existing Jupyte…