Related papers: Constant in an Ever-Changing World
The advances in unsupervised object-centric representation learning have significantly improved its application to downstream tasks. Recent works highlight that disentangled object representations can aid policy learning in image-based,…
This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be…
To imitate the ability of keeping learning of human, continual learning which can learn from a never-ending data stream has attracted more interests recently. In all settings, the online class incremental learning (OCIL), where incoming…
We provide a new method for online learning, specifically prediction with expert advice, in a changing environment. In a non-changing environment the Squint algorithm has been designed to always function at least as well as other known…
In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals. The duration between decisions becomes a crucial hyperparameter, as setting it too short may increase the problem's difficulty by…
Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task…
This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties. We propose a combination of a Reinforcement Learning (RL) based policy in the outer loop suitably chosen to ensure…
We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of…
We present a Multi-task Soft Actor-Critic (SAC) Reinforcement Learning framework designed for open-system quantum control across diverse Hamiltonians, which learns optimal pulse sequences while simultaneously discovering problem-specific…
Continual Learning (CL) is a powerful tool that enables agents to learn a sequence of tasks, accumulating knowledge learned in the past and using it for problem-solving or future task learning. However, existing CL methods often assume that…
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…
We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with…
Continuous reinforcement learning such as DDPG and A3C are widely used in robot control and autonomous driving. However, both methods have theoretical weaknesses. While DDPG cannot control noises in the control process, A3C does not satisfy…
A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training. In this paper, we approach this challenge through the following invariance principle: an agent…
This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major limitations of…
The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…
Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is modeled as a stream of tasks drawn from a task…
In continual learning (CL), an AI agent (e.g., autonomous vehicles or robotics) learns from non-stationary data streams under dynamic environments. For the practical deployment of such applications, it is important to guarantee robustness…
Reinforcement learning (RL) has had its fair share of success in contact-rich manipulation tasks but it still lags behind in benefiting from advances in robot control theory such as impedance control and stability guarantees. Recently, the…
As humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision…