Autonomous Intersection Management on Large example grid
11.2Total Travel Time (s)RL-based AIM solution (TRPO)
Evaluation results
| Method | Links | |
|---|---|---|
| RL-based AIM solution (TRPO)Algorithm=TRPO, Backbone=MLP (3 hidden layers, 100 units each), Library=rllab, Environment=OpenAI Gym2017.05 | 11.2 |