colosseum.mdp.base_infinite

View Source

 1import abc
 2from typing import TYPE_CHECKING
 3
 4from colosseum.mdp import BaseMDP
 5
 6if TYPE_CHECKING:
 7    from colosseum.mdp import NODE_TYPE
 8
 9
10class ContinuousMDP(BaseMDP, abc.ABC):
11    """
12    The base class for continuous MDPs.
13    """
14
15    @staticmethod
16    def is_episodic() -> bool:
17        return False
18
19    def get_grid_representation(self, node: "NODE_TYPE", h: int = None):
20        return super(ContinuousMDP, self)._get_grid_representation(node)

class ContinuousMDP(colosseum.mdp.base.BaseMDP, abc.ABC): View Source

11class ContinuousMDP(BaseMDP, abc.ABC):
12    """
13    The base class for continuous MDPs.
14    """
15
16    @staticmethod
17    def is_episodic() -> bool:
18        return False
19
20    def get_grid_representation(self, node: "NODE_TYPE", h: int = None):
21        return super(ContinuousMDP, self)._get_grid_representation(node)

The base class for continuous MDPs.

@staticmethod

def is_episodic() -> bool: View Source

16    @staticmethod
17    def is_episodic() -> bool:
18        return False

Returns

bool: True if the MDP is episodic.

def get_grid_representation( self, node: Union[colosseum.mdp.custom_mdp.CustomNode, colosseum.mdp.river_swim.base.RiverSwimNode, colosseum.mdp.deep_sea.base.DeepSeaNode, colosseum.mdp.frozen_lake.base.FrozenLakeNode, colosseum.mdp.simple_grid.base.SimpleGridNode, colosseum.mdp.minigrid_empty.base.MiniGridEmptyNode, colosseum.mdp.minigrid_rooms.base.MiniGridRoomsNode, colosseum.mdp.taxi.base.TaxiNode], h: int = None): View Source

20    def get_grid_representation(self, node: "NODE_TYPE", h: int = None):
21        return super(ContinuousMDP, self)._get_grid_representation(node)

Returns

np.ndarray: An ASCII representation of the state given in input stored as numpy array.

Inherited Members

colosseum.mdp.base.BaseMDP: BaseMDP; get_unique_symbols; get_available_hardness_measures; produce_gin_file_from_mdp_parameters; does_seed_change_MDP_structure; sample_parameters; sample_mdp_parameters; get_node_class; n_actions; parameters; get_gin_parameters; get_gin_config; get_node_labels; get_node_action_labels; hash; instantiate_MDP; T; R; recurrent_nodes_set; communication_class; get_optimal_policy; get_worst_policy; get_value_functions; optimal_value_functions; worst_value_functions; random_value_functions; optimal_transition_probabilities; worst_transition_probabilities; random_transition_probabilities; optimal_markov_chain; worst_markov_chain; random_markov_chain; get_stationary_distribution; optimal_stationary_distribution; worst_stationary_distribution; random_stationary_distribution; optimal_average_rewards; worst_average_rewards; random_average_rewards; get_average_reward; optimal_average_reward; worst_average_reward; random_average_reward; transition_matrix_and_rewards; graph_layout; graph_metrics; diameter; sum_reciprocals_suboptimality_gaps; discounted_value_norm; undiscounted_value_norm; value_norm; measures_of_hardness; summary; hardness_report; get_info_class; get_transition_distributions; get_reward_distribution; sample_reward; get_measure_from_name; action_spec; observation_spec; get_observation; reset; step; random_steps; random_step; get_visitation_counts; reset_visitation_counts; get_value_node_labels
dm_env._environment.Environment: reward_spec; discount_spec; close