On the Role of Reward Functions for Reinforcement Learning in the Traffic Assignment Problem.
Ricardo GrunitzkiGabriel de Oliveira RamosPublished in: IJCNN (2020)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- policy search
- markov decision processes
- optimal policy
- state space
- markov decision process
- partially observable
- inverse reinforcement learning
- function approximation
- transition model
- simple examples
- transition probabilities
- multi agent
- multiple agents
- control policies
- state variables
- model free
- continuous state
- state action
- machine learning
- learning agent
- np hard
- probabilistic model
- higher order
- information extraction
- temporal difference
- infinite horizon