-
It was removed to mitigate #2479
@tohaklim Is https://uk.wikipedia.org/wiki/%D0%9C%D0%B5%D1%80%D0%B5%D0%B6%D0%B0_%D0%90%D0%97%D0%A1_%D0%9F%D1%80%D0%B8%D0%B2%D0%B0%D1%82 describing generic fuel sta…
-
Im working with an environment that has a very high memory usage. This usually prevents any sort of Async Sampling, since copies of the environment are very expensive. Is there any example of working …
-
![pong_stack](https://user-images.githubusercontent.com/11839520/50086051-90902000-0204-11e9-8a3a-868fc787904d.png)
Experiment: coach -r -p Atari_A3C -lvl pong
During my Pong experiment after arou…
-
I am running the examples on my Ubuntu machine Intel® Core i7-4770K CPU @ 3.50GHz with 4 cores. During the entire training, only ~25% of the CPU is used. Which means it is running on only one core. Am…
-
### Describe the problem
https://groups.google.com/forum/#!topic/ray-dev/dk0erEEnkFY
In DQN, DDPG, IMPALA, and A3C, the gradients() function for the tf policy graph is overriden, but does not incl…
ericl updated
5 years ago
-
Make sure we understand the algorithm along with how PPO would be implemented in the structure.
-
I'm getting an Attribute error while trying to configure my NAF agent:
```
nafConfig = Configuration.from_json('naf_agent.json') #Copied from examples.
net = layered_network_builder([dict(type='d…
admcl updated
5 years ago
-
Hi!
Thanks for your great work.
I wanted to collect data (i.e., a vast range of observations and a vast range of actions) in CARLA to test an algorithm. There are two options:
**Option 1:** Use…
-
First of all, thanks for your work.
I was reading the A2RL paper, and I wonder what the value output V(st , θv ) exactly is , what is the formulation?
-
Greetings!
First off, great work with the library and rapid advancement of AI environments for experimentation.
I have a few questions regarding parallel operation of the gym retro environments.…
ghost updated
5 years ago