Environments¶

EnvironmentInfo¶

class nnabla_rl.environments.environment_info.EnvironmentInfo(observation_space, action_space, max_episode_steps, unwrapped_env, reward_function: Optional[Callable[[Any, Any, Dict], int]] = None)[source]¶

Environment Information class

This class contains the basic information of the target training environment.

property action_dim¶: The dimension of action assuming that the action is flatten.

property action_high¶: The upper limit of action space

property action_low¶: The lower limit of action space

property action_shape¶: The shape of action space

static from_env(env)[source]¶

Create env_info from environment

Parameters: env (gym.Env) – the environment
Returns: EnvironmentInfo (EnvironmentInfo)

Example

>>> import gym
>>> from nnabla_rl.environments.environment_info import EnvironmentInfo
>>> env = gym.make("CartPole-v0")
>>> env_info = EnvironmentInfo.from_env(env)
>>> env_info.state_shape
(4,)

is_continuous_action_env()[source]¶

Check whether the action to execute in the environment is continuous or not

Returns

True if the action to execute in the environment is continuous. Otherwise False.: Note that if the action is gym.spaces.Tuple and all of the element are continuous, it returns True.

Return type

bool

is_continuous_state_env()[source]¶

Check whether the state of the environment is continuous or not

Returns

True if the state of the environment is continuous. Otherwise False.: Note that if the state is gym.spaces.Tuple and all of the element are continuous, it returns True.

Return type

bool

is_discrete_action_env()[source]¶

Check whether the action to execute in the environment is discrete or not

Returns

True if the action to execute in the environment is discrete. Otherwise False.: Note that if the action is gym.spaces.Tuple and all of the element are discrete, it returns True.

Return type

bool

is_discrete_state_env()[source]¶

Check whether the state of the environment is discrete or not

Returns

True if the state of the environment is discrete. Otherwise False.: Note that if the state is gym.spaces.Tuple and all of the element are discrete, it returns True.

Return type

bool

is_goal_conditioned_env()[source]¶

Check whether the environment is gym.GoalEnv or not

Returns: True if the environment is gym.GoalEnv. Otherwise False.
Return type: bool

is_tuple_state_env()[source]¶

Check whether the state of the environment is tuple or not

Returns: True if the state of the environment is tuple. Otherwise False.
Return type: bool

property state_dim¶: The dimension of state assuming that the state is flatten.

property state_high¶: The upper limit of observation space

property state_low¶: The lower limit of observation space

property state_shape¶: The shape of observation space