-
PC Configuration: Ubuntu 20.04, RTX 3060, RAM 64 gb, Cuda 11.4, Nvidia driver 470.141.03.
Note: For Cartpole and Ant simulation, same command works but not for Anymal.
I was trying the demo run…
-
Hi guys,
Thanks a lot for the codebase you open-sourced.
I'm trying to build on your implementation of model-based offline algorithms (mainly COMBO) to use it with other types of generative mode…
-
Hi,
I recently started migrating my JAX agents to use the new LocalLayout, which incorporates the changes that simplify the setup for ensuring that running non-distributed agents would not block. I…
-
I get this error when loading a trained model
Whta does it mean?
ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group
-
Just setting up an issue to track this progress. @lockwo had previously expressed interest in this. A related resource is CleanRL is now introducing a refactored [sac implementation](https://github.co…
-
Dear @takuseno,
I was trying build a categorical critic (c51) from the paper [A Distributional Perspective on Reinforcement Learning](https://arxiv.org/pdf/1707.06887.pdf) into your d3rlpy library. …
-
Thanks for this excellent work!
I have some questions about the code implements.
1. In `core.py` line 214, you do `torch.clamp()` to `log_std`. Why we need `clamp()` here, could it be that `log…
-
Hi,
I'm trying to run some of the examples. While the Ant task works fine, other robots lead to a segfault during the initialize_task() function. This includes both the cartpole and franke_cabinet …
-
TorchBench CI has detected a performance signal.
Base PyTorch version: 1.11.0.dev20220203+cu113
Base PyTorch commit: 58dabebcd746aad95a37bdfc7e60e5d22f0f5641
Affected PyTorch version: 1.12.0.dev20…
-
### Search before asking
- [X] I searched the [issues](https://github.com/ray-project/ray/issues) and found no similar issues.
### Ray Component
Ray Core
### What happened + What you expected to …