Medium¶

Description¶

The data is collected from the HumanoidStandup environment. The Agent was trained with Stable Baselines 3’s implementation of SAC for \(10 \cdot 10^6\) steps, without the cinert, cvel, qfcr_actuator, cfrc_ext observations. This “medium” policy causes the agent to rise to an unstable position, fall over, and then stand in a knee-high position.

Dataset Specs¶


Total Steps	1000000
Total Episodes	1000
Dataset Observation Space	`Box(-inf, inf, (348,), float64)`
Dataset Action Space	`Box(-0.4, 0.4, (17,), float32)`
Algorithm	SB3/SAC
Author	Kallinteris Andreas
Email	kallinteris@protonmail.com
Code Permalink	https://github.com/Farama-Foundation/minari-dataset-generation-scripts
Minari Version	`0.5.2` (supported)
Download	`minari download mujoco/humanoidstandup/medium-v0`

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('mujoco/humanoidstandup/medium-v0')
env  = dataset.recover_environment()


ID	HumanoidStandup-v5
entry_point	`gymnasium.envs.mujoco.humanoidstandup_v5:HumanoidStandupEnv`
max_episode_steps	1000
reward_threshold	None
nondeterministic	`False`
order_enforce	`True`
disable_env_checker	`False`
kwargs	`{}`
additional_wrappers	`(WrapperSpec(name='Monitor', entry_point='stable_baselines3.common.monitor:Monitor', kwargs=None),)`
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('mujoco/humanoidstandup/medium-v0')
env  = dataset.recover_environment()
eval_env = dataset.recover_environment(eval_env=True)

assert env.spec == eval_env.spec