Benchmarks for reinforcement learning in mixed-autonomy traffic.
Eugene VinitskyAboudy KreidiehLuc Le FlemNishant KheterpalKathy JangFangyu WuRichard LiawEric LiangAlexandre M. BayenPublished in: CoRL (2018)
Keyphrases
- reinforcement learning
- function approximation
- traffic flow
- network traffic
- multi agent systems
- markov decision processes
- benchmark suite
- temporal difference learning
- state space
- dynamic programming
- multi agent
- temporal difference
- traffic data
- learning algorithm
- road network
- multi agent reinforcement learning
- reinforcement learning algorithms
- road traffic
- traffic patterns
- traffic congestion
- real time
- traffic volume
- traffic control
- internet traffic
- congestion control
- traffic conditions
- website
- learning process
- transfer learning