LunarLander-v2
LunarLander-v2
LunarLander-v2 - Imitation Learning Datasets
This is a dataset created by Imitation Learning Datasets project.
It was created by using Stable Baselines weights from a PPO policy from HuggingFace.
Description
The dataset consists of 1,000 episodes with an average episodic reward of 500.
Each entry consists of:
obs (list): observation with length 8.
action (int): action (0, 1, 2 and 3).
reward (float): reward point for that timestep.
episode_returns (bool): if that state… See the full description on the dataset page: https://huggingface.co/datasets/NathanGavenski/LunarLander-v2.ppo-LunarLander-v2