-
Hello,
I'm studying the DreamerV1 implementation in your repository, and I have a question about how the weights are synchronized between the player and the main models (world_model, actor).
In the …
-
On Linux Debian "testing" and
``` bash
$ java -version
openjdk version "21.0.5" 2024-10-15
OpenJDK Runtime Environment (build 21.0.5+11-Debian-1)
OpenJDK 64-Bit Server VM (build 21.0.5+11-Debian…
-
Hi veRL team, thanks for open-sourcing the great framework. I have successfully run the ppo training of qwen2-7b using 2 nodes, so I think there is no problem with my environment. But I encountered an…
-
We have a fair number of constituents tagged with a tms constituent type of "couple" (I'm guessing a custom value but obviously a common real world use case).
Are couples modeled together as Perso…
-
Consider using actor model for performance / distributed run / avoiding complicated error handling when config.
-
Unfortunately I discovered on their discord last night that Actix is going to be deprecated in a few months. The recommendation the Actix team have been suggesting is to follow the patterns within [th…
-
![{F6370F54-615A-412F-94A8-A9C0897C3626}](https://github.com/user-attachments/assets/969282da-c6c9-45db-b614-53dea8f3c8b8)
We cannot linearly derive the architecture from the requirements… Stakehol…
-
'exp_name': 'puckworld1D_cont_CDiscDDPG', 'env_name': 'puckworld_continuous_1d', 'env_type': 'csuite', 'agent_name': 'CD_DDPG', 'nonlinear': True, 'exp_type': 'control', 'render': False, 'num_runs': 5…
zhrli updated
3 weeks ago
-
### What is the problem?
```python
# get an existing worker pool
udfMaster = ray.get_actor("model_predict")
# get a worker from worker pool, the worker is also a actor
worker = ray.get(ud…
-
This is a discussion thread to dig into the theory surrounding how this project *is* (like) an *actor model* system and how it *is* or *isn't* compatible with [structured concurrency](https://trio.dis…