Partial

Description

The partial dataset includes other tasks being performed, but there are subtrajectories where the 4 target subtasks are completed in sequence.

Dataset Specs

Total Steps	156560
Total Episodes	621
Dataset Observation Space	Dict('achieved_goal': Dict('kettle': Box(-inf, inf, (7,), float64), 'light switch': Box(-inf, inf, (2,), float64), 'microwave': Box(-inf, inf, (1,), float64), 'slide cabinet': Box(-inf, inf, (1,), float64)), 'desired_goal': Dict('kettle': Box(-inf, inf, (7,), float64), 'light switch': Box(-inf, inf, (2,), float64), 'microwave': Box(-inf, inf, (1,), float64), 'slide cabinet': Box(-inf, inf, (1,), float64)), 'observation': Box(-inf, inf, (59,), float64))
Dataset Action Space	Box(-1.0, 1.0, (9,), float64)
Algorithm	None
Author	Rodrigo de Lazcano
Email	rperezvicente@farama.org
Code Permalink	https://github.com/rodrigodelazcano/d4rl-minari-dataset-generation
Minari Version	0.4.3 (supported)
Download	minari download D4RL/kitchen/partial-v2

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('D4RL/kitchen/partial-v2')
env  = dataset.recover_environment()

ID	FrankaKitchen-v1
Observation Space	Dict('achieved_goal': Dict('kettle': Box(-inf, inf, (7,), float64), 'light switch': Box(-inf, inf, (2,), float64), 'microwave': Box(-inf, inf, (1,), float64), 'slide cabinet': Box(-inf, inf, (1,), float64)), 'desired_goal': Dict('kettle': Box(-inf, inf, (7,), float64), 'light switch': Box(-inf, inf, (2,), float64), 'microwave': Box(-inf, inf, (1,), float64), 'slide cabinet': Box(-inf, inf, (1,), float64)), 'observation': Box(-inf, inf, (59,), float64))
Action Space	Box(-1.0, 1.0, (9,), float64)
entry_point	gymnasium_robotics.envs.franka_kitchen:KitchenEnv
max_episode_steps	450
reward_threshold	None
nondeterministic	False
order_enforce	True
disable_env_checker	False
kwargs	{'remove_task_when_completed': False, 'terminate_on_tasks_completed': False, 'tasks_to_complete': ['microwave', 'kettle', 'light switch', 'slide cabinet']}
additional_wrappers	()
vector_entry_point	None

Evaluation Environment Specs

This dataset doesn’t contain an eval_env_spec attribute which means that the specs of the environment used for evaluation are the same as the specs of the environment used for creating the dataset. The following calls will return the same environment:

import minari

dataset = minari.load_dataset('D4RL/kitchen/partial-v2')
env  = dataset.recover_environment()
eval_env = dataset.recover_environment(eval_env=True)

assert env.spec == eval_env.spec