Reinforcement Learning Agent under Partial Observability for Traffic Light Control in Presence of Gridlocks.
Thanapapas HorsuwanChaodit AswakulPublished in: SUMO (2019)
Keyphrases
- partial observability
- learning agent
- reinforcement learning
- state space
- solving problems
- learning algorithm
- learning capabilities
- reinforcement learning algorithms
- learning tasks
- learning process
- single agent
- model free
- reward function
- partially observable
- function approximation
- dynamic environments
- orders of magnitude
- transfer learning
- temporal difference
- markov decision processes
- neural network
- planning problems
- sufficient conditions
- domain knowledge
- machine learning