Reinforcement Learning for Mapping Instructions to Actions.
S. R. K. BranavanHarr ChenLuke S. ZettlemoyerRegina BarzilayPublished in: ACL/IJCNLP (2009)
Keyphrases
- reinforcement learning
- perceptual aliasing
- action selection
- action space
- partially observable
- state and action spaces
- state space
- function approximation
- reward function
- action sets
- partial observability
- loop closure
- markov decision processes
- learning algorithm
- partially observable domains
- reinforcement learning algorithms
- plan recognition
- behavioural cloning
- optimal policy
- multiagent reinforcement learning
- temporal difference
- human actions
- human activities
- robotic control
- multi agent
- learning process
- macro actions
- decision theoretic
- agent receives
- neural network
- supervised learning
- markov decision process
- optimal control
- actor critic
- sensory inputs
- state action
- learning agent