Umaze-Dense

Description

The data is collected from the PointMaze_UMazeDense-v3 environment, which contains a U shape maze. The agent uses a PD controller to follow a path of waypoints generated with QIteration until it reaches the goal. The task is continuing which means that when the agent reaches the goal the environment generates a new random goal without resetting the location of the agent. The reward function is dense, being the negative Euclidean distance between the goal and the agent. To add variance to the collected paths random noise is added to the actions taken by the agent.

Dataset Specs

Total Timesteps	1000000
Total Episodes	13289
Dataset Observation Space	Dict('achieved_goal': Box(-inf, inf, (2,), float64), 'desired_goal': Box(-inf, inf, (2,), float64), 'observation': Box(-inf, inf, (4,), float64))
Dataset Action Space	Box(-1.0, 1.0, (2,), float32)
Algorithm	QIteration
Author	Rodrigo Perez-Vicente
Email	rperezvicente@farama.org
Code Permalink	https://github.com/rodrigodelazcano/d4rl-minari-dataset-generation
Minari Version	~=0.4
download	minari.download_dataset("pointmaze-umaze-dense-v1")

Environment Specs

ID	PointMaze_UMazeDense-v3
Action Space	Box(-1.0, 1.0, (2,), float32)
Observation Space	Dict('achieved_goal': Box(-inf, inf, (2,), float64), 'desired_goal': Box(-inf, inf, (2,), float64), 'observation': Box(-inf, inf, (4,), float64))