Look-Ahead Insertion Policy for a Shared-Taxi System Based on Reinforcement Learning.
Chong WeiYinhu WangXuedong YanChunfu ShaoPublished in: IEEE Access (2018)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- partially observable environments
- function approximators
- reward function
- reinforcement learning problems
- actor critic
- partially observable
- reinforcement learning algorithms
- action space
- policy gradient
- state and action spaces
- function approximation
- approximate dynamic programming
- markov decision processes
- markov decision problems
- control policy
- state space
- control policies
- decision problems
- learning algorithm
- state action
- rl algorithms
- approximate policy iteration
- partially observable domains
- average reward
- policy iteration
- model free
- learning classifier systems
- optimal control
- neural network
- policy evaluation
- multi agent reinforcement learning
- inverse reinforcement learning
- agent learns
- partially observable markov decision processes
- dynamic programming
- infinite horizon
- finite state
- model free reinforcement learning
- sufficient conditions
- robotic control
- control problems
- asymptotically optimal
- reinforcement learning methods