Perceptual Reward Functions.
Ashley D. EdwardsCharles Lee Isbell Jr.Atsuo TakanishiPublished in: CoRR (2016)
Keyphrases
- reward function
- markov decision processes
- state space
- inverse reinforcement learning
- reinforcement learning
- multiple agents
- optimal policy
- reinforcement learning algorithms
- policy search
- simple examples
- state variables
- transition probabilities
- markov decision process
- transition model
- human visual system
- learning algorithm
- generative model
- state action
- optimal solution
- initially unknown