Related papers: Self-Creating Random Walks for Decentralized Learn…

Real-world reinforcement learning (RL) offers a promising approach to training precise and dexterous robotic manipulation policies in an online manner, enabling robots to learn from their own experience while gradually reducing human labor.…

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…

Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby,…

As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn…

Although robotic imitation learning (RIL) is promising for embodied intelligent robots, existing RIL approaches rely on computationally intensive multi-model trajectory predictions, resulting in slow execution and limited real-time…

Existing metrics for reinforcement learning (RL) such as regret, PAC bounds, or uniform-PAC (Dann et al., 2017), typically evaluate the cumulative performance, while allowing the agent to play an arbitrarily bad policy at any finite time t.…

From natural language processing to genome sequencing, large-scale machine learning models are bringing advances to a broad range of fields. Many of these models are too large to be trained on a single machine, and instead must be…

Designing effective task sequences is crucial for curriculum reinforcement learning (CRL), where agents must gradually acquire skills by training on intermediate tasks. A key challenge in CRL is to identify tasks that promote exploration,…

Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch…

We investigate a multi-agent planning problem, where each agent aims to achieve an individual task while avoiding collisions with others. We assume that each agent's task is expressed as a Time-Window Temporal Logic (TWTL) specification…

Self-driving cars and autonomous driving research has been receiving considerable attention as major promising prospects in modern artificial intelligence applications. According to the evolution of advanced driver assistance system (ADAS),…

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the…

Cellular-based networks are expected to offer connectivity for massive Internet of Things (mIoT) systems. However, their Random Access CHannel (RACH) procedure suffers from unreliability, due to the collision from the simultaneous massive…

Manipulating the interaction trajectories between the intelligent agent and the environment can control the agent's training and behavior, exposing the potential vulnerabilities of reinforcement learning (RL). For example, in Cyber-Physical…

It is challenging to use reinforcement learning (RL) in cyber-physical systems due to the lack of safety guarantees during learning. Although there have been various proposals to reduce undesired behaviors during learning, most of these…

Self-imitation learning is a Reinforcement Learning (RL) method that encourages actions whose returns were higher than expected, which helps in hard exploration and sparse reward problems. It was shown to improve the performance of…

On-line motion planning in unknown environments is a challenging problem as it requires (i) ensuring collision avoidance and (ii) minimizing the motion time, while continuously predicting where to go next. Previous approaches to on-line…

Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL is catastrophic forgetting, which arises when performance on…

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be…

As AI systems become increasingly autonomous, reliably aligning their decision-making with human preferences is essential. Inverse reinforcement learning (IRL) offers a promising approach to infer preferences from demonstrations. These…