Related papers: CANDERE-COACH: Reinforcement Learning from Noisy F…
We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in…
Robots are extending their presence in domestic environments every day, being more common to see them carrying out tasks in home scenarios. In the future, robots are expected to increasingly perform more complex tasks and, therefore, be…
Inverse reinforcement learning (IRL) is the problem of inferring the reward function of an agent, given its policy or observed behavior. Analogous to RL, IRL is perceived both as a problem and as a class of methods. By categorically…
Reinforcement learning (RL) is a popular machine learning paradigm for game playing, robotics control, and other sequential decision tasks. However, RL agents often have long learning times with high data requirements because they begin by…
Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…
Robust real-world learning should benefit from both demonstrations and interactions with the environment. Current approaches to learning from demonstration and reward perform supervised learning on expert demonstration data and use…
Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering…
Learning from human feedback is an effective way to improve robotic learning in exploration-heavy tasks. Compared to the wide application of binary human feedback, scalar human feedback has been used less because it is believed to be noisy…
This article studies inverse reinforcement learning (IRL) for the stochastic linear-quadratic optimal control problem, where two agents are considered. A learner agent does not know the expert agent's performance cost function, but it…
Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on…
Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these…
Deep Reinforcement Learning (DRL) has become a powerful methodology to solve complex decision-making problems. However, DRL has several limitations when used in real-world problems (e.g., robotics applications). For instance, long training…
In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…
Understanding the simultaneously very diverse and intricately fine-grained set of possible human actions is a critical open problem in computer vision. Manually labeling training videos is feasible for some action classes but doesn't scale…
Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy.…
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…
Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs). However, it is highly data demanding, so unfeasible in physical systems for most applications.…
Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose…
In recent times, reinforcement learning has produced baffling results when it comes to performing control tasks with highly non-linear systems. The impressive results always outweigh the potential vulnerabilities or uncertainties associated…
The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and…