coopihc.policy.BasePolicy.BasePolicy

class BasePolicy(*args, action_state=None, **kwargs)[source]

Bases: object

Base Policy class. Randomly samples from the action state. You have can provide an action state as an argument (args[0]). If no action state is provided, the policy is initialized with an action state with a single ‘None’ action.

Methods

`default_value`	Apply this decorator to use bundle.game_state as default value to observe if game_state = None
`reset`	Reset the policy
`sample`

Attributes

`action`	Return the last action.
`action_keys`
`observation`	Return the last observation.
`parameters`
`state`
`unwrapped`

property action

Return the last action.

Returns: last action
Return type: State<coopihc.base.StateElement.StateElement>

default_value()[source]: Apply this decorator to use bundle.game_state as default value to observe if game_state = None

property observation

Return the last observation.

Returns: last observation
Return type: State<coopihc.base.State.State>

reset(random=True)[source]

Reset the policy

Parameters: random (bool, optional) – reset the policy, defaults to True. Here in case of subclassing BasePolicy.