Expert¶

Description¶

A Minari dataset for AntMaze (expert level, check docs), generated from the ‘AntMaze_Large_Diverse_GR-v5’ environment.

Dataset Specs¶


Total Steps	1000000
Total Episodes	1000
Dataset Observation Space	`Dict('achieved_goal': Box(-inf, inf, (2,), float64), 'desired_goal': Box(-inf, inf, (2,), float64), 'observation': Box(-inf, inf, (105,), float64))`
Dataset Action Space	`Box(-1.0, 1.0, (8,), float32)`
Algorithm	QIteration+SAC
Author	Lukasz Sawala
Email	lukaszsawala2003@gmail.com
Code Permalink	https://github.com/LukaszSawala/Farama-Antmaze-Dataset-Generation
Minari Version	`0.5.3` (supported)
Download	`minari download antmaze-large-diverserandom/expert-v1`

Environment Specs¶

The following table rows correspond to the Gymnasium environment specifications used to generate the dataset. To read more about what each parameter means you can have a look at the Gymnasium documentation https://gymnasium.farama.org/api/registry/#gymnasium.envs.registration.EnvSpec

This environment can be recovered from the Minari dataset as follows:

import minari

dataset = minari.load_dataset('hf://lukasz-sawala-goat/antmaze-large-diverserandom/expert-v1')
env  = dataset.recover_environment()

Evaluation Environment Specs¶

This environment can be recovered from the Minari dataset as follows:

import minari

dataset = minari.load_dataset('hf://lukasz-sawala-goat/antmaze-large-diverserandom/expert-v1')
eval_env  = dataset.recover_environment(eval_env=True)