FlattenObservation

class fluidgym.wrappers.flatten_obs.FlattenObservation(env: FluidEnvLike)

Bases: FluidWrapper

A wrapper that flattens the observation space.

It flattens each observation tensor in the observation dictionary.

Parameters:

env (FluidEnvLike) – The environment to wrap.

property observation_space: Box

The observation space of the environment.

reset(seed: int | None = None, randomize: bool | None = None) → tuple[Tensor, dict[str, Tensor]]

Resets the environment to an initial internal state, returning an initial observation and info.

Parameters:

• seed (int | None) – The seed to use for random number generation. If None, the current seed is used.

• randomize (bool | None) – Whether to randomize the initial state. If None, the default behavior is used.

Returns:

A tuple containing the initial observation and an info dictionary.

Return type:

tuple[torch.Tensor, dict[str, torch.Tensor]]

step(action: Tensor) → tuple[Tensor, Tensor, bool, bool, dict[str, Tensor]]

Run one timestep of the environment’s dynamics using the agent actions.

When the end of an episode is reached (terminated or truncated), it is necessary to call reset() to reset this environment’s state for the next episode.

Parameters:

action (torch.Tensor) – The action to take.

Returns:

A tuple containing the flattened observation, reward, terminated flag, truncated flag, and info dictionary.

Return type:

tuple[torch.Tensor, torch.Tensor, bool, bool, dict[str, torch.Tensor]]