Partially Observable Reinforcement Learning for Intelligent Transportation Systems.
Rusheng ZhangAkihiro IshikawaWenli WangBenjamin StrinerOzan K. TonguzPublished in: CoRR (2018)
Keyphrases
- partially observable
- intelligent transportation systems
- reinforcement learning
- markov decision processes
- state space
- wireless communication
- partially observable domains
- traffic flow
- partial observability
- traffic management
- dynamical systems
- markov decision problems
- partially observable environments
- decision problems
- autonomous vehicles
- traffic congestion
- reward function
- reinforcement learning algorithms
- infinite horizon
- optimal policy
- wireless networks
- control strategies
- learning algorithm
- robot control
- ubiquitous computing
- computer simulation
- machine learning
- belief state
- planning domains
- optimal control
- communication networks
- multiagent systems