-
I'm working on distributed deep reinforcement learning. Any advice is helpful!
Vogen updated
7 years ago
-
Hi @ebonyclock , I am trying to train a healthpack agent with your newest code, after training for a day, I found the performance of the agent is declining.
![image](https://user-images.githubuserc…
-
While I'm implementing models in A3C, I tried to allocate a fraction of gpu to a process and processes that use multiple fractions of gpus update a parameters of a parameter server (in a single machin…
-
Hello Yuxin,
I am doing training on Atari Game and I noticed that utilization of gpu ( nvidia smi -l ) is very low ( ~ 10-50%). Could you comment that, please?
[nvidia-smi-l.txt](https://github.…
ghost updated
7 years ago
-
When using dist kv store, launch.py while create several subprocesses with different DMLC_ROLE, "schedule", "worker" or "server". And after that, kv store would works automatically.
I want to manua…
Vogen updated
7 years ago
-
I would like to experiment with meta-RL, but the central idea involves adding the previous prediction and its quality to the input vector at each timestep.
This means I'll be writing my own train l…
-
Hi,
Finally got around to trying a real "deep learning" implementation against btgym and I've run up against a problem. I really don't know enough about openai gym to understand what the problem is…
-
Does cpp-package support multiple GPUs parallel training?
I am trying to implement A3C using cpp-package.
I saw another thread "How to run on multiple GPUs - python". https://github.com/dmlc/mxne…
-
This plan captures our work from early August to mid September. We will ship around September 15th. Major work items of this iteration include Volta 16bit support and C#/.NET API. There will also be n…
-
Hi there,
awesome work! I noticed that play.py doesn't compile due to a shape difference between the policy and the action space in your choose_action() function. However, by limiting the size of the…