amago.envs.builtin.toy_gym

amago.envs.builtin.toy_gym#

Custom toy gym environments.

Classes

MetaFrozenLake(size[, k_episodes, ...])

A version of gym's toy FrozenLake problem that demonstrates the strengths of black-box meta-RL.

RoomKeyDoor([dark, size, max_episode_steps, ...])

A version of the Dark Room Key-Door Env.
class MetaFrozenLake(size, k_episodes=10, hard_mode=False, recover_mode=False)[source]#

Bases: Env

A version of gym’s toy FrozenLake problem that demonstrates the strengths of black-box meta-RL. The agent begins in an unknown lake layout and has k attempts to find and exploit a path to the goal. The concept of k explicit attempts can be removed and replaced with long trials that penalize failure without resets. Explicit partial observability can be added in the form of noisy sensor observations. Discrete action indices can be shuffled between tasks.

Parameters:

  • size (int) – The size of the lake map (n x n grid).

  • k_episodes (int) – The number of attempts agents have on each new lake layout.

  • hard_mode (bool) – If True, randomly shuffle discrete action indices on reset and add noise to the agent’s position sensors. Randomly create “holes” in the ice behind the agent’s path to penalize backtracking. These changes introduce partial observability and increase memory demands. Defaults to False.

  • recover_mode (bool) – If False, falling through the ice terminates the episode. If True, the agent is allowed to recover to its previous position but receives a penalty. Defaults to False.

make_obs(reset_signal)[source]#
render(*args, **kwargs)[source]#

Compute the render frames as specified by render_mode during the initialization of the environment.

The environment’s metadata render modes (env.metadata["render_modes"]) should contain the possible ways to implement the render modes. In addition, list versions for most render modes is achieved through gymnasium.make which automatically applies a wrapper to collect rendered frames.

Note

As the render_mode is known during __init__, the objects used to render the environment state should be initialised in __init__.

By convention, if the render_mode is:

  • None (default): no render is computed.

  • “human”: The environment is continuously rendered in the current display or terminal, usually for human consumption. This rendering should occur during step() and render() doesn’t need to be called. Returns None.

  • “rgb_array”: Return a single frame representing the current state of the environment. A frame is a np.ndarray with shape (x, y, 3) representing RGB values for an x-by-y pixel image.

  • “ansi”: Return a strings (str) or StringIO.StringIO containing a terminal-style text representation for each time step. The text can include newlines and ANSI escape sequences (e.g. for colors).

  • “rgb_array_list” and “ansi_list”: List based version of render modes are possible (except Human) through the wrapper, gymnasium.wrappers.RenderCollection that is automatically applied during gymnasium.make(..., render_mode="rgb_array_list"). The frames collected are popped after render() is called or reset().

Note

Make sure that your class’s metadata "render_modes" key includes the list of supported modes.

Changed in version 0.25.0: The render function was changed to no longer accept parameters, rather these parameters should be specified in the environment initialised, i.e., gymnasium.make("CartPole-v1", render_mode="human")

reset(*args, **kwargs)[source]#

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

This method generates a new starting state often with some randomness to ensure that the agent explores the state space and learns a generalised policy about the environment. This randomness can be controlled with the seed parameter otherwise if the environment already has a random number generator and reset() is called with seed=None, the RNG is not reset.

Therefore, reset() should (in the typical use case) be called with a seed right after initialization and then never again.

For Custom environments, the first line of reset() should be super().reset(seed=seed) which implements the seeding correctly.

Changed in version v0.25: The return_info parameter was removed and now info is expected to be returned.

Parameters:

  • seed (optional int) – The seed that is used to initialize the environment’s PRNG (np_random). If the environment does not already have a PRNG and seed=None (the default option) is passed, a seed will be chosen from some source of entropy (e.g. timestamp or /dev/urandom). However, if the environment already has a PRNG and seed=None is passed, the PRNG will not be reset. If you pass an integer, the PRNG will be reset even if it already exists. Usually, you want to pass an integer right after the environment has been initialized and then never again. Please refer to the minimal example above to see this paradigm in action.

  • options (optional dict) – Additional information to specify how the environment is reset (optional, depending on the specific environment)

Returns:

Observation of the initial state. This will be an element of observation_space

(typically a numpy array) and is analogous to the observation returned by step().

info (dictionary): This dictionary contains auxiliary information complementing observation. It should be analogous to

the info returned by step().

Return type:

observation (ObsType)

soft_reset()[source]#
step(action)[source]#

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.

Changed in version 0.26: The Step API was changed removing done in favor of terminated and truncated to make it clearer to users when the environment had terminated or truncated which is critical for reinforcement learning bootstrapping algorithms.

Parameters:

action (ActType) – an action provided by the agent to update the environment state.

Returns:

An element of the environment’s observation_space as the next observation due to the agent actions.

An example is a numpy array containing the positions and velocities of the pole in CartPole.

reward (SupportsFloat): The reward as a result of taking the action. terminated (bool): Whether the agent reaches the terminal state (as defined under the MDP of the task)

which can be positive or negative. An example is reaching the goal state or moving into the lava from the Sutton and Barton, Gridworld. If true, the user needs to call reset().

truncated (bool): Whether the truncation condition outside the scope of the MDP is satisfied.

Typically, this is a timelimit, but could also be used to indicate an agent physically going out of bounds. Can be used to end the episode prematurely before a terminal state is reached. If true, the user needs to call reset().

info (dict): Contains auxiliary diagnostic information (helpful for debugging, learning, and logging).

This might, for instance, contain: metrics that describe the agent’s performance state, variables that are hidden from observations, or individual reward terms that are combined to produce the total reward. In OpenAI Gym <v26, it contains “TimeLimit.truncated” to distinguish truncation and termination, however this is deprecated in favour of returning terminated and truncated variables.

done (bool): (Deprecated) A boolean value for if the episode has ended, in which case further step() calls will

return undefined results. This was removed in OpenAI Gym v26 in favor of terminated and truncated attributes. A done signal may be emitted for different reasons: Maybe the task underlying the environment was solved successfully, a certain timelimit was exceeded, or the physics simulation has entered an invalid state.

Return type:

observation (ObsType)

class RoomKeyDoor(dark=True, size=9, max_episode_steps=50, meta_rollout_horizon=500, start_location='random', key_location='random', goal_location='random', randomize_actions=False)[source]#

Bases: Env

A version of the Dark Room Key-Door Env.

Based on Algorithm Distillation (Laskin et al., 2022).

Parameters:

  • dark (bool) – If True, the key and door position are hidden from the agent. If False, they are revealed, which is an easy way to demonstrate that meta-learning problems are created by partial observability. Defaults to True.

  • size (int) – The size of the grid (n x n). Defaults to 9.

  • max_episode_steps (int) – The maximum number of steps in each episode before the task is reset. Defaults to 50.

  • meta_rollout_horizon (int) – The agent has this many timsteps to adapt to each world layout. The best solution is to infer the key and door locations and then solve the task as many times as possible within this time limit. Defaults to 500.

  • start_location (tuple[int, int] | str) – The starting location of the agent. Defaults to “random”. Can also be set to a specific (x, y) coordinate.

  • key_location (tuple[int, int] | str) – The location of the key. Defaults to “random”. Can also be set to a specific (x, y) coordinate.

  • goal_location (tuple[int, int] | str) – The location of the goal. Defaults to “random”. Can also be set to a specific (x, y) coordinate.

  • randomize_actions (bool) – If True, the discrete action indices are randomly shuffled on each reset. Defaults to False.

generate_task()[source]#
obs()[source]#
render(*args, **kwargs)[source]#

Compute the render frames as specified by render_mode during the initialization of the environment.

The environment’s metadata render modes (env.metadata["render_modes"]) should contain the possible ways to implement the render modes. In addition, list versions for most render modes is achieved through gymnasium.make which automatically applies a wrapper to collect rendered frames.

Note

As the render_mode is known during __init__, the objects used to render the environment state should be initialised in __init__.

By convention, if the render_mode is:

  • None (default): no render is computed.

  • “human”: The environment is continuously rendered in the current display or terminal, usually for human consumption. This rendering should occur during step() and render() doesn’t need to be called. Returns None.

  • “rgb_array”: Return a single frame representing the current state of the environment. A frame is a np.ndarray with shape (x, y, 3) representing RGB values for an x-by-y pixel image.

  • “ansi”: Return a strings (str) or StringIO.StringIO containing a terminal-style text representation for each time step. The text can include newlines and ANSI escape sequences (e.g. for colors).

  • “rgb_array_list” and “ansi_list”: List based version of render modes are possible (except Human) through the wrapper, gymnasium.wrappers.RenderCollection that is automatically applied during gymnasium.make(..., render_mode="rgb_array_list"). The frames collected are popped after render() is called or reset().

Note

Make sure that your class’s metadata "render_modes" key includes the list of supported modes.

Changed in version 0.25.0: The render function was changed to no longer accept parameters, rather these parameters should be specified in the environment initialised, i.e., gymnasium.make("CartPole-v1", render_mode="human")

reset(*args, **kwargs)[source]#

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

This method generates a new starting state often with some randomness to ensure that the agent explores the state space and learns a generalised policy about the environment. This randomness can be controlled with the seed parameter otherwise if the environment already has a random number generator and reset() is called with seed=None, the RNG is not reset.

Therefore, reset() should (in the typical use case) be called with a seed right after initialization and then never again.

For Custom environments, the first line of reset() should be super().reset(seed=seed) which implements the seeding correctly.

Changed in version v0.25: The return_info parameter was removed and now info is expected to be returned.

Parameters:

  • seed (optional int) – The seed that is used to initialize the environment’s PRNG (np_random). If the environment does not already have a PRNG and seed=None (the default option) is passed, a seed will be chosen from some source of entropy (e.g. timestamp or /dev/urandom). However, if the environment already has a PRNG and seed=None is passed, the PRNG will not be reset. If you pass an integer, the PRNG will be reset even if it already exists. Usually, you want to pass an integer right after the environment has been initialized and then never again. Please refer to the minimal example above to see this paradigm in action.

  • options (optional dict) – Additional information to specify how the environment is reset (optional, depending on the specific environment)

Returns:

Observation of the initial state. This will be an element of observation_space

(typically a numpy array) and is analogous to the observation returned by step().

info (dictionary): This dictionary contains auxiliary information complementing observation. It should be analogous to

the info returned by step().

Return type:

observation (ObsType)

reset_same_task()[source]#
step(action)[source]#

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.

Changed in version 0.26: The Step API was changed removing done in favor of terminated and truncated to make it clearer to users when the environment had terminated or truncated which is critical for reinforcement learning bootstrapping algorithms.

Parameters:

action (ActType) – an action provided by the agent to update the environment state.

Returns:

An element of the environment’s observation_space as the next observation due to the agent actions.

An example is a numpy array containing the positions and velocities of the pole in CartPole.

reward (SupportsFloat): The reward as a result of taking the action. terminated (bool): Whether the agent reaches the terminal state (as defined under the MDP of the task)

which can be positive or negative. An example is reaching the goal state or moving into the lava from the Sutton and Barton, Gridworld. If true, the user needs to call reset().

truncated (bool): Whether the truncation condition outside the scope of the MDP is satisfied.

Typically, this is a timelimit, but could also be used to indicate an agent physically going out of bounds. Can be used to end the episode prematurely before a terminal state is reached. If true, the user needs to call reset().

info (dict): Contains auxiliary diagnostic information (helpful for debugging, learning, and logging).

This might, for instance, contain: metrics that describe the agent’s performance state, variables that are hidden from observations, or individual reward terms that are combined to produce the total reward. In OpenAI Gym <v26, it contains “TimeLimit.truncated” to distinguish truncation and termination, however this is deprecated in favour of returning terminated and truncated variables.

done (bool): (Deprecated) A boolean value for if the episode has ended, in which case further step() calls will

return undefined results. This was removed in OpenAI Gym v26 in favor of terminated and truncated attributes. A done signal may be emitted for different reasons: Maybe the task underlying the environment was solved successfully, a certain timelimit was exceeded, or the physics simulation has entered an invalid state.

Return type:

observation (ObsType)

Contents