-
Generate the dataloaders for the following datasets.
saint.___.: coyo-dataset on mini-gpt.
@snat-s: OKVQA, VQA-V2
We need some help with the following:
Multimodal C4.
Classic C4.
Conceptual…
-
Understanding the schema and format of the control datasets so as to craft optimal prompts for zero-shot and fine-tuned eval of closed source VLMs on control tasks.
-
Hi，it is me again (hhh
When I run the example like this：
```
import d3rlpy
# prepare dataset
dataset, env = d3rlpy.datasets.get_d4rl('hopper-medium-v0')
# prepare algorithm
cql = d3rlpy.alg…
-
Hi, thanks for you d3rlpy, which is a great job. I have some questions about this implementation, could you please help me?
1. What is the difference between MDPDataset.terminals and MDPDataset.epi…
-
There are some datasets right now that Daniel helped translated for control using the minari format.
The code to translate from the original to minari format can be found [here](https://github.com/…
-
**Vision-Language datasets/ replacements that are good to go:**
1. [OBELICS](https://huggingface.co/datasets/HuggingFaceM4/OBELICS)
2. [COYO-700M](https://github.com/kakaobrain/coyo-dataset)
3. […
-
Writing this without fixes for now, things I'm noticing going through the library:
1. The dataset listed in README doesn't seem to exist. This is bad, as that's the first thing a beginner will like…
-
Thank you for your excellent work!
In case of misunderstanding something, I am writing to ensure that in the offline RL setting, when using evaluators={"environment": d3rlpy.metrics.EnvironmentEvalua…
-
## Motivation
Want to add the Gen DGRL Dataset for benchmarking RL algorithms in a easy & efficient way
## Solution
Use D4RL wrapper (https://github.com/Farama-Foundation/D4RL) to download an…
-
Hi,
I find that action values in some datasets (e.g., BallCircle, CarCircle, DroneCircle) are out of bounds of environments (i.e., [-1, 1]). However, the actions in D4RL are bounded, and when using…