Related papers: Enter the Matrix: Safely Interruptible Autonomous …
Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i.e., a condition in which new incoming information strongly…
Can humans get arbitrarily capable reinforcement learning (RL) agents to do their bidding? Or will sufficiently capable RL agents always find ways to bypass their intended objectives by shortcutting their reward signal? This question…
Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area…
Autonomous multiple tasks learning is a fundamental capability to develop versatile artificial agents that can act in complex environments. In real-world scenarios, tasks may be interrelated (or "hierarchical") so that a robot has to first…
Modern control theories such as systems engineering approaches try to solve nonlinear system problems by revelation of causal relationship or co-relationship among the components; most of those approaches focus on control of sophisticatedly…
A wide variety of goals could cause an AI to disable its off switch because "you can't fetch the coffee if you're dead" (Russell 2019). Prior theoretical work on this shutdown problem assumes that humans know everything that AIs do. In…
Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…
Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…
Autonomous driving at unsignalized intersections is still considered a challenging application for machine learning due to the complications associated with handling complex multi-agent scenarios characterized by a high degree of…
Autonomous racing serves as a critical platform for evaluating automated driving systems and enhancing vehicle mobility intelligence. This work investigates offline reinforcement learning methods to train agents within the dynamic F1tenth…
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement…
Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots. While most approaches in the Safe Reinforcement Learning area do not require prior knowledge of constraints and robot…
Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other…
The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…
Machine and reinforcement learning (RL) are increasingly being applied to plan and control the behavior of autonomous systems interacting with the physical world. Examples include self-driving vehicles, distributed sensor networks, and…
Practitioners often rely on compute-intensive domain randomization to ensure reinforcement learning policies trained in simulation can robustly transfer to the real world. Due to unmodeled nonlinearities in the real system, however, even…
We propose a model-free reinforcement learning method for controlling mixed autonomy traffic in simulated traffic networks with through-traffic-only two-way and four-way intersections. Our method utilizes multi-agent policy decomposition…
Safety is a primary concern when applying reinforcement learning to real-world control tasks, especially in the presence of external disturbances. However, existing safe reinforcement learning algorithms rarely account for external…
Reinforcement learning has emerged as a promising methodology for training robot controllers. However, most results have been limited to simulation due to the need for a large number of samples and the lack of automated-yet-safe data…
Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…