In recent years, deep reinforcement learning (DRL) algorithms have been widely studied and utilized in the area of Intelligent Transportation Systems (ITS). DRL agents are mostly trained with transition pairs and interaction trajectories generated from simulation, and they can achieve satisfying or near optimal performances under familiar input states. However, for relative rare visited or even unvisited regions in the state space, there is no guarantee that the agent could perform well. Unfortunately, novel conditions are inevitable in real-world problems and there is always a gap between the real data and simulated data. Therefore, to implement DRL algorithms in real-world transportation systems, we should not only train the agent learn a policy that maps states to actions, but also the model uncertainty associated with each action. In this study, we adapt the method of Bayesian ensemble to train a group of agents with imposed diversity for an energy management system of a delivery vehicle. The agents in the ensemble agree well on familiar states but show diverse results on unfamiliar or novel states. This uncertainty estimation facilitates the implementation of interpretable postprocessing modules which can ensure robust and safe operations under high uncertainty conditions.
|Original language||English (US)|
|Number of pages||7|
|State||Published - 2020|
|Event||31st IEEE Intelligent Vehicles Symposium, IV 2020 - Virtual, Las Vegas, United States|
Duration: Oct 19 2020 → Nov 13 2020
|Conference||31st IEEE Intelligent Vehicles Symposium, IV 2020|
|City||Virtual, Las Vegas|
|Period||10/19/20 → 11/13/20|
Bibliographical noteFunding Information:
*Corresponding author The information, data, or work presented herein was funded in part by the Advanced Research Projects Agency-Energy (ARPA-E) U.S. Department of Energy, under Award Number DE-AR0000795.
ACKNOWLEDGMENT The information, data, or work presented herein was funded in part by the Advanced Research Projects Agency-Energy (ARPA-E) U.S. Department of Energy, under Award Number DE-AR0000795. The views and opinions of authors expressed herein do not necessarily state or reflect those of thenUitedtSteasoGvernment or anygaencyetrehof.
© 2020 IEEE.