benchmarl.environments.VmasTask

class VmasTask(value)[source]

Bases: Task

Enum for VMAS tasks.

BALANCE = 1

SAMPLING = 2

NAVIGATION = 3

TRANSPORT = 4

REVERSE_TRANSPORT = 5

WHEEL = 6

DISPERSION = 7

MULTI_GIVE_WAY = 8

DROPOUT = 9

GIVE_WAY = 10

WIND_FLOCKING = 11

PASSAGE = 12

JOINT_PASSAGE = 13

JOINT_PASSAGE_SIZE = 14

BALL_PASSAGE = 15

BALL_TRAJECTORY = 16

BUZZ_WIRE = 17

FLOCKING = 18

DISCOVERY = 19

FOOTBALL = 20

SIMPLE_ADVERSARY = 21

SIMPLE_CRYPTO = 22

SIMPLE_PUSH = 23

SIMPLE_REFERENCE = 24

SIMPLE_SPEAKER_LISTENER = 25

SIMPLE_SPREAD = 26

SIMPLE_TAG = 27

SIMPLE_WORLD_COMM = 28

static associated_class()[source]: The associated task class

classmethod env_name() → str: The name of the environment in the benchmarl/conf/task folder

get_task(config: Dict[str, Any] | None = None) → TaskClass

Get the TaskClass object associated with this enum element by passing it the task name and config.

If no config is given, it will be loaded from benchmarl/conf/task/self.env_name()/self.name using Task.get_from_yaml().

Parameters:

config (dict) – Optional configuration of the task.
provided (If not)
yaml. (the default configuration will be loaded from)

Returns:

The TaskClass object for the task.

get_from_yaml(path: str | None = None) → TaskClass

Load the task configuration from yaml

Parameters:: path (str, optional) – The full path of the yaml file to load from. If None, it will default to benchmarl/conf/task/self.env_name()/self.name
Returns:: the TaskClass with the loaded config

property config

update_config(config: Dict[str, Any]) → Task

supports_continuous_actions() → bool

supports_discrete_actions() → bool

max_steps(env: EnvBase) → int

has_render(env: EnvBase) → bool

group_map(env: EnvBase) → Dict[str, List[str]]

observation_spec(env: EnvBase) → Composite

info_spec(env: EnvBase) → Composite | None

state_spec(env: EnvBase) → Composite | None

action_spec(env: EnvBase) → Composite

action_mask_spec(env: EnvBase) → Composite | None

static log_info(batch: TensorDictBase) → Dict[str, float]

get_reward_sum_transform(env: EnvBase) → Transform

get_env_transforms(env: EnvBase) → List[Transform]

get_replay_buffer_transforms(env: EnvBase, group: str) → List[Transform]

static render_callback(experiment, env: EnvBase, data: TensorDictBase)