Simple 2D environment containing a point and a goal location.
PointEnv(goal=np.array((1.0, 1.0), dtype=np.float32), arena_size=5.0, done_bonus=0.0, never_done=False, max_episode_length=math.inf)¶
A simple 2D point environment.
goal (np.ndarray) – A 2D array representing the goal position
arena_size (float) – The size of arena where the point is constrained within (-arena_size, arena_size) in each dimension
done_bonus (float) – A numerical bonus added to the reward once the point as reached the goal
never_done (bool) – Never send a done signal, even if the agent achieves the goal
max_episode_length (int) – The maximum steps allowed for an episode.
akro.Space: The action space specification.
akro.Space: The observation space specification.
EnvSpec: The environment specification.
list: A list of string representing the supported render modes.
Reset the environment.
- The first observation conforming to
- dict: The episode-level information.
Note that this is not part of env_info provided in step(). It contains information of he entire episode， which could be needed to determine the first action (e.g. in the case of goal-conditioned or MTRL.)
- Return type
Step the environment.
Renders the environment.
Creates a visualization of the environment.
Close the env.
Sample a list of num_tasks tasks.