Expert#

Description#

Trajectories have expert data from a fine-tuned RL policy provided in the DAPG repository. The environment used to collect the dataset is AdroitHandPen-v1.

Dataset Specs#

Total Timesteps

499206

Total Episodes

4958

Flatten Observations

False

Flatten Actions

False

Algorithm

None

Author

Rodrigo de Lazcano

Email

rperezvicente@farama.org

Code Permalink

https://github.com/rodrigodelazcano/d4rl-minari-dataset-generation

download

minari.download_dataset("pen-expert-v0")

Environment Specs#

ID

AdroitHandPen-v1

Action Space

Box(-1.0, 1.0, (24,), float32)

Observation Space

Box(-inf, inf, (45,), float64)