Related papers: Automatic Curricula via Expert Demonstrations

Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it…

Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones, while maintaining stable performance across all possible class sequences. In real-world settings, the order in…

Applications of Reinforcement Learning (RL) in robotics are often limited by high data demand. On the other hand, approximate models are readily available in many robotics scenarios, making model-based approaches like planning a…

In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods. RL algorithms have become…

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

Inverse Reinforcement Learning (IRL) learns an optimal policy, given some expert demonstrations, thus avoiding the need for the tedious process of specifying a suitable reward function. However, current methods are constrained by at least…

Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the RL-Agent from…

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than…

Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact…

Deep Reinforcement Learning (or just "RL") is gaining popularity for industrial and research applications. However, it still suffers from some key limits slowing down its widespread adoption. Its performance is sensitive to initial…

Dynamic material handling (DMH) involves the assignment of dynamically arriving material transporting tasks to suitable vehicles in real time for minimising makespan and tardiness. In real-world scenarios, historical task records are…

Existing end-to-end autonomous driving (AD) algorithms typically follow the Imitation Learning (IL) paradigm, which faces challenges such as causal confusion and an open-loop gap. In this work, we propose RAD, a 3DGS-based closed-loop…

Developing decision-making algorithms for highly automated driving systems remains challenging, since these systems have to operate safely in an open and complex environments. Reinforcement Learning (RL) approaches can learn comprehensive…

Recent work has shown that reinforcement learning (RL) is a promising approach to control dynamical systems described by partial differential equations (PDE). This paper shows how to use RL to tackle more general PDE control problems that…

Most reinforcement learning (RL) platforms use high-level programming languages, such as OpenAI Gymnasium using Python. These frameworks provide various API and benchmarks for testing RL algorithms in different domains, such as autonomous…

This paper proposes, implements, and evaluates a reinforcement learning (RL)-based computational framework for automatic mesh generation. Mesh generation plays a fundamental role in numerical simulations in the area of computer aided design…

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

Chain-of-thought reasoning, where language models expend additional computation by producing thinking tokens prior to final responses, has driven significant advances in model capabilities. However, training these reasoning models is…

Non-parametric episodic memory can be used to quickly latch onto high-rewarded experience in reinforcement learning tasks. In contrast to parametric deep reinforcement learning approaches in which reward signals need to be back-propagated…

Acquiring complex behaviors is essential for artificially intelligent agents, yet learning these behaviors in high-dimensional settings poses a significant challenge due to the vast search space. Traditional reinforcement learning (RL)…