Abstract | ||
---|---|---|
The use of reinforcement learning (RL) in multiagent scenarios is challenging. I consider the route choice problem, where drivers must choose routes that minimise their travel times. Here, selfish RL-agents must adapt to each others' decisions. In this work, I show how the agents can learn (with performance guarantees) by minimising the regret associated with their decisions, thus achieving the User Equilibrium (UE). Considering the UE is inefficient from a global perspective, I also focus on bridging the gap between the UE and the system optimum. In contrast to previous approaches, this work drops any full knowledge assumption. |
Year | DOI | Venue |
---|---|---|
2017 | 10.5555/3091125.3091470 | AAMAS |
Keywords | Field | DocType |
regret,route choice,multiagent reinforcement learning | Regret,Computer science,Simulation,Bridging (networking),Operations research,Reinforcement learning,Distributed computing | Conference |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gabriel de Oliveira Ramos | 1 | 14 | 4.84 |