相关论文: Reward (Mis)design for Autonomous Driving

Designers of AI agents often iterate on the reward function in a trial-and-error process until they get the desired behavior, but this only guarantees good behavior in the training environment. We propose structuring this process as a…

A model used for velocity control during car following was proposed based on deep reinforcement learning (RL). To fulfil the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was…

In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment…

Automated Driving (AD) systems have the potential to increase safety, comfort and energy efficiency. Recently, major automotive companies have started testing and validating AD systems (ADS) on public roads. Nevertheless, the commercial…

Autonomous driving is getting a lot of attention in the last decade and will be the hot topic at least until the first successful certification of a car with Level 5 autonomy. There are many public datasets in the academic community.…

Effective leveraging of real-world driving datasets is crucial for enhancing the training of autonomous driving systems. While Offline Reinforcement Learning enables training autonomous vehicles with such data, most available datasets lack…

It is expected that many human drivers will still prefer to drive themselves even if the self-driving technologies are ready. Therefore, human-driven vehicles and autonomous vehicles (AVs) will coexist in a mixed traffic for a long time. To…

In recent years, a variety of tasks have been accomplished by deep reinforcement learning (DRL). However, when applying DRL to tasks in a real-world environment, designing an appropriate reward is difficult. Rewards obtained via actual…

The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally capable agents. However, the success of RL agents is often highly…

This paper presents an interpretable reward design framework for reinforcement learning based constrained optimal control problems with state and terminal constraints. The problem is formalized within a standard partially observable Markov…

In model-based reinforcement learning it is typical to decouple the problems of learning the dynamics model and learning the reward function. However, when the dynamics model is flawed, it may generate erroneous states that would never…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Learning reward functions remains the bottleneck to equip a robot with a broad repertoire of skills. Large Language Models (LLM) contain valuable task-related knowledge that can potentially aid in the learning of reward functions. However,…

Autonomous parallel-style on-ramp merging in human controlled traffic continues to be an existing issue for autonomous vehicle control. Existing non-learning based solutions for vehicle control rely on rules and optimization primarily.…

The primary focus of autonomous driving research is to improve driving accuracy. While great progress has been made, state-of-the-art algorithms still fail at times. Such failures may have catastrophic consequences. It therefore is…

Adaptive traffic signal control is one key avenue for mitigating the growing consequences of traffic congestion. Incumbent solutions such as SCOOT and SCATS require regular and time-consuming calibration, can't optimise well for multiple…

Safety constraints and optimality are important, but sometimes conflicting criteria for controllers. Although these criteria are often solved separately with different tools to maintain formal guarantees, it is also common practice in…

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error…

The rapid integration of Artificial Intelligence (AI)-based systems offers benefits for various domains of the economy and society but simultaneously raises concerns due to emerging scandals. These scandals have led to the increasing…

In cooperative multi-agent reinforcement learning (MARL), how to design a suitable reward signal to accelerate learning and stabilize convergence is a critical problem. The global reward signal assigns the same global reward to all agents…