DECSTR: Learning Goal-Directed Abstract Behaviors using Pre-Verbal Spatial Predicates in Intrinsically Motivated Agents.
Ahmed AkakziaCédric ColasPierre-Yves OudeyerMohamed ChetouaniOlivier SigaudPublished in: CoRR (2020)
Keyphrases
- goal directed
- learning algorithm
- learning process
- autonomous learning
- learning agents
- reinforcement learning
- multi agent
- dynamic environments
- minority game
- machine learning
- multiagent learning
- state transitions
- autonomous robots
- spatial and temporal
- learning systems
- mobile robot
- multi agent systems
- learning tasks
- decision theoretic
- knowledge level
- learning capabilities
- intelligent agents
- rational agents
- learned knowledge
- intelligent behavior
- spatio temporal