Easy-to-use D4RL offline dataset loader
Project description
just-d4rl
Easy-to-use D4RL offline dataset loader
Installation
pip install just-d4rl
Usage
from just_d4rl import D4RLDataset, d4rl_offline_dataset
dataset = d4rl_offline_dataset("hopper-medium-v2")
dataset = d4rl_offline_dataset("walker2d-random-v2")
dataset = d4rl_offline_dataset("halfcheetah-medium-expert-v2")
dataset = d4rl_offline_dataset("antmaze-umaze-v2")
dataset = d4rl_offline_dataset("hopper-medium-v2")
dataset['observations'].shape, dataset['actions'].shape, dataset['rewards'].shape, dataset['next_observations'].shape, dataset['terminals'].shape
# ((1000000, 11),
# (1000000, 11),
# (1000000, 3),
# (1000000,),
# (1000000,))
dataset = d4rl_offline_dataset("hopper-medium-v2")
dataset = D4RLDataset(d4rl_dataset)
batch = dataset[-16:]
batch["observation"].shape, batch["action"].shape, batch["reward"].shape, batch["next_observation"].shape, batch["terminal"].shape
# (torch.Size([16, 11]),
# torch.Size([16, 3]),
# torch.Size([16]),
# torch.Size([16, 11]),
# torch.Size([16]),
# torch.Size([16]))
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
just_d4rl-0.2407.2.tar.gz
(8.6 kB
view details)
Built Distribution
File details
Details for the file just_d4rl-0.2407.2.tar.gz
.
File metadata
- Download URL: just_d4rl-0.2407.2.tar.gz
- Upload date:
- Size: 8.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.12.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 81c3a5917ad115ff121bf3ed7ab62bea856c3448af45855f4892d83bc45ec90c |
|
MD5 | 5e7d5bf6e1e09df40a6bdd4916bf7059 |
|
BLAKE2b-256 | 5af20f93ed1ebd37d74be16180b0bf91caeec4f9b6adb25488172c1458a90608 |
File details
Details for the file just_d4rl-0.2407.2-py3-none-any.whl
.
File metadata
- Download URL: just_d4rl-0.2407.2-py3-none-any.whl
- Upload date:
- Size: 6.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.12.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f3928fcb1a6c6a2bad5c176504b10bd2f5ec35f4e36d43e57a89fc47ececf926 |
|
MD5 | 61f21b8db0b5ecfbce5c0c3584fd1252 |
|
BLAKE2b-256 | dde243a369d1bc93e46b62fb4dec78d54d5fd51ab44ad4cf0c78d53ad3e5099e |