Interference and Shaping in Sensorimotor Adaptations with Rewards.
Ran DarshanArthur LebloisDavid HanselPublished in: PLoS Comput. Biol. (2014)
Keyphrases
- reward shaping
- reinforcement learning
- complex domains
- goal directed
- perception action
- markov decision processes
- cognitive development
- multiarmed bandit
- long term and short term
- embodied cognition
- credit assignment
- reinforcement learning algorithms
- free riding
- bandit problems
- reward function
- genetic algorithm
- language acquisition
- symbol grounding
- image sequences
- frequency hopping
- real world