Robust Deep Reinforcement Learning Scheduling via Weight Anchoring
Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired behavior in Neural Networks. Weight anchoring may be used to find a solution to a learning problem that is nearby the solution of another learning problem. Thereby, learning can be carried out in optimal environments without neglecting or unlearning desired behavior. We demonstrate this approach on the example of learning mixed QoS-efficient discrete resource scheduling with infrequent priority messages. Results show that this method provides performance comparable to the state of the art of augmenting a simulation environment, alongside significantly increased robustness and steerability.
Code (1)
Tasks
Continual LearningDeep Reinforcement Learningreinforcement-learningReinforcement LearningSchedulingSimilar Papers 제목 키워드 기반
Graph-Enhanced Deep Reinforcement Learning for Multi-Objective Unrelated Parallel Machine Scheduling
The Unrelated Parallel Machine Scheduling Problem (UPMSP) with release dates, setups, and eligibility constraints presents a significant multi-objective challenge. Traditional methods struggle to balance minimizing Total…
Reinforcement LearningGraph Neural NetworkDecentralized Task Scheduling in Distributed Systems: A Deep Reinforcement Learning Approach
Efficient task scheduling in large-scale distributed systems presents significant challenges due to dynamic workloads, heterogeneous resources, and competing quality-of-service requirements. Traditional centralized appro…
Reinforcement LearningAAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models
Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback. SFT provides a useful behavio…
Reinforcement LearningContinual GUI Agents
As digital environments (data distribution) are in flux, with new GUI data arriving over time-introducing new domains or resolutions-agents trained on static environments deteriorate in performance. In this work, we intr…
Continual LearningTracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after dr…
Reinforcement Learning