Related papers: Q-learning-based Model-free Safety Filter
Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…
Safety stands as the primary obstacle preventing the widespread adoption of learning-based robotic systems in our daily lives. While reinforcement learning (RL) shows promise as an effective robot learning paradigm, conventional RL…
Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of…
Reinforcement Learning in domains with sparse rewards is a difficult problem, and a large part of the training process is often spent searching the state space in a more or less random fashion for any learning signals. For control problems,…
Setting up and controlling optical systems is often a challenging and tedious task. The high number of degrees of freedom to control mirrors, lenses, or phases of light makes automatic control challenging, especially when the complexity of…
This paper explores the application of a reinforcement learning (RL) framework using the Q-Learning algorithm to enhance dynamic pricing strategies in the retail sector. Unlike traditional pricing methods, which often rely on static demand…
Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model…
Safety remains an open problem in reinforcement learning (RL), especially during training. While safety filters are promising to address safe exploration, they are generally poorly suited for high-dimensional systems with unknown dynamics.…
This paper introduces a new method for safety-aware robot learning, focusing on repairing policies using predictive models. Our method combines behavioral cloning with neural network repair in a two-step supervised learning framework. It…
Mainstream approximate action-value iteration reinforcement learning (RL) algorithms suffer from overestimation bias, leading to suboptimal policies in high-variance stochastic environments. Quantile-based action-value iteration methods…
Imitation learning (IL) enables agents to acquire skills directly from expert demonstrations, providing a compelling alternative to reinforcement learning. However, prior online IL approaches struggle with complex tasks characterized by…
Applications of reinforcement learning (RL) to stabilization problems of real systems are restricted since an agent needs many experiences to learn an optimal policy and may determine dangerous actions during its exploration. If we know a…
Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment…
Ensuring strict safety guarantees is the paramount challenge for emerging 5G/6G wireless systems, particularly as they increasingly govern mission-critical applications ranging from autonomous UAV swarms to industrial automation. While deep…
Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the early stages of learning in noisy environments, because much effort is spent unlearning biased estimates of the state-action value function. The bias…
The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid unsafe states. This…
Designing control policies for legged locomotion is complex due to the under-actuated and non-continuous robot dynamics. Model-free reinforcement learning provides promising tools to tackle this challenge. However, a major bottleneck of…
Soft Q-learning has emerged as a versatile model-free method for entropy-regularised reinforcement learning, optimising for returns augmented with a penalty on the divergence from a reference policy. Despite its success, the multi-step…
Ensuring human safety in collaborative robotics can compromise efficiency because traditional safety measures increase robot cycle time when human interaction is frequent. This paper proposes a safety-aware approach to mitigate efficiency…
Reinforcement learning (RL) has proven to be particularly effective in solving complex decision-making problems for a wide range of applications. Safe reinforcement learning refers to a class of constrained problems where the constraint…