Related papers: Policy-Based Deep Reinforcement Learning Hyperheur…

The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reaction to stochastic disturbances and global optimization of production goals. Conventional priority rules are insufficiently flexible to…

Learning-assisted hyper-heuristics can select among dispatching rules while preserving the feasibility and interpretability of constructive Job Shop Scheduling Problem (JSSP) heuristics. Their main computational cost lies in label…

The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the meta reinforcement learning literature much recent work has…

This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained…

To achieve scenario intelligence, humans must transfer knowledge to robots by developing goal-oriented algorithms, which are sometimes insensitive to dynamically changing environments. While deep reinforcement learning achieves significant…

One of the key challenges in applying reinforcement learning to real-life problems is that the amount of train-and-error required to learn a good policy increases drastically as the task becomes complex. One potential solution to this…

In recent years, the robotics community has made substantial progress in robotic manipulation using deep reinforcement learning (RL). Effectively learning of long-horizon tasks remains a challenging topic. Typical RL-based methods…

Competitive analysis of online algorithms has commonly been applied to understand the behaviour of real-time systems during overload conditions. While competitive analysis provides insight into the behaviour of certain algorithms, it is…

Deep reinforcement learning can match or exceed human performance in stable contexts, but with minor changes to the environment artificial networks, unlike humans, often cannot adapt. Humans rely on a combination of heuristics to simplify…

Humans decompose novel complex tasks into simpler ones to exploit previously learned skills. Analogously, hierarchical reinforcement learning seeks to leverage lower-level policies for simple tasks to solve complex ones. However, because…

The Flexible Job-shop Scheduling Problem (FJSP) is a classical combinatorial optimization problem that has a wide-range of applications in the real world. In order to generate fast and accurate scheduling solutions for FJSP, various deep…

The dynamic vehicle dispatching problem corresponds to deciding which vehicles to assign to requests that arise stochastically over time and space. It emerges in diverse areas, such as in the assignment of trucks to loads to be transported;…

In this work, we focus on addressing the long-horizon manipulation tasks in densely cluttered scenes. Such tasks require policies to effectively manage severe occlusions among objects and continually produce actions based on visual…

This study develops a framework based on reinforcement learning to dynamically manage a large portfolio of search operators within meta-heuristics. Using the idea of tabu search, the framework allows for continuous adaptation by temporarily…

We investigate the feasibility of deploying Deep-Q based deep reinforcement learning agents to job-shop scheduling problems in the context of modular production facilities, using discrete event simulations for the environment. These…

In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a reinforcement learning agent based on the Deep Deterministic…

Job-shop scheduling problem (JSP) is a mathematical optimization problem widely used in industries like manufacturing, and flexible JSP (FJSP) is also a common variant. Since they are NP-hard, it is intractable to find the optimal solution…

We present a reinforcement learning based framework for human-centered collaborative systems. The framework is proactive and balances the benefits of timely actions with the risk of taking improper actions by minimizing the total time spent…

The learning order of semantic classes significantly impacts unsupervised domain adaptation for semantic segmentation, especially under adverse weather conditions. Most existing curricula rely on handcrafted heuristics (e.g., fixed…

Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy…