Skill Discovery¶
MMLF skill discovery interface
This module defines the interface for skill discovery methods
- The following methods must be implemented by each skill discovery method:
- tellStateTransition(self, state, action, reward, succState):
Inform skill discovery of a new transition and search for new skills.
- episodeFinished():
Inform skill discovery that an episode has terminated.
- class resources.skill_discovery.skill_discovery.SkillDiscovery(optionCreationFct, stateSpace, *args, **kwargs)¶
The skill discovery interface.
New in version 0.9.9.
- static create(skillDiscoverySpec, optionCreationFct, stateSpace)¶
Factory method that creates skill discovery based on spec-dictionary.
- episodeFinished(terminalState)¶
Inform skill discovery method that the current episode terminated.
- static getSkillDiscoveryDict()¶
Returns dict that contains a mapping from skill discovery name to class.
- tellStateTransition(state, action, reward, succState)¶
Inform skill discovery method about a new state transition.
The agent has transitioned from state to succState after executing action and obtaining the reward reward.
Returns a pair consisting of the list of discovered options and whether a new option was discovered based on this state transition.
Predefined Skills¶
Local Graph Partitioning¶
