Expert

Description

The data is collected from the [Walker2d](https://gymnasium.farama.org/environments/mujoco/walker2d/) environment. The Agent was trained with Stable Baselines 3’s implementation of SAC for \(25 \cdot 10^6\) steps. This “expert” policy runs with a wide gait very fast, while falling rarely.

Dataset Specs

Total Steps	999190
Total Episodes	1000
Dataset Observation Space	Box(-inf, inf, (17,), float64)
Dataset Action Space	Box(-1.0, 1.0, (6,), float32)
Algorithm	SB3/{algorithm_name}
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/walker2d/expert-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/walker2d/expert-v0')
env  = dataset.recover_environment()

ID	Walker2d-v5
Observation Space	Box(-inf, inf, (17,), float64)
Action Space	Box(-1.0, 1.0, (6,), float32)
entry_point	gymnasium.envs.mujoco.walker2d_v5:Walker2dEnv
max_episode_steps	1000
reward_threshold	None
nondeterministic	False
order_enforce	True
disable_env_checker	False
kwargs	{}
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('mujoco/walker2d/expert-v0')
env  = dataset.recover_environment()
eval_env = dataset.recover_environment(eval_env=True)

assert env.spec == eval_env.spec