-
I am trying to develop a distributed model free algorithm for ride sharing using deep reinforcement learning. I want to create a simulator design that uses Deep Q techniques to learn optimal dispatch …
-
Hello, does the lib support multi-agent environment?
Or more precisely, allow multiple agents share environment state, select their action in parallel, then return the combined actions to the environ…
-
This one looks interesting.
> In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the …
-
Hi Aurelien,
I know you are busy. If time permits can you upload the solutions to chapter 15. Thanks. Pardon me to ask this, did you include any new materials to version 2 of this book **Hands-On M…
-
### System information
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**: Yes
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Linux …
-
Currently, we know that human trained 6x128 is around 2600-2700 elo in CGOS, but how strong is the 5x64 version network? would be interesting to compare the current zero one with a human trained one n…
-
> AI - 人工智能;AR - 增强现实;CV - 机器视觉;DL - 深度学习;DM - 数据挖掘;DS - 数据科学;DV - 数据可视化;IOT - 物联网;ML - 机器学习;NLP - 自然语言处理
-
Hi, I am trying to run the repo in a Docker. That can make the installation smoother.
I get the following error:
```
root@de47041b77ca:/n64# python2 test.py
[2019-01-25 23:40:55,630] Making new…
-
On current master - my use case would be if I want to `pip install -e . -v` Ray from source on 2+ conda environments. As far as I can tell, the Bazel build system has to run / compile everything for e…
-
Did you have the performance summary of the RL based quantization performance on MobileNet? Given that you have described about this here : https://pocketflow.github.io/reinforcement_learning/