Research map / Reinforcement learning / Visual and representation RL
Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling
Inguk Choi, Woo-Jin Shin, Sanghyun Cho, Hyun-Jung Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a multi-policy RL framework with self-evolution for job scheduling problems to improve exploration and generalization over single-decision-maker RL dispatching methods.
Problem
RL-based job scheduling methods train only a single decision-maker, limiting exploration and performance; designing reward functions for different JSP variants is also hard and generalization across variants is a concern.
Approach
Trains multiple scheduling policies jointly with a self-evolution mechanism instead of a single decision-maker, aiming to improve exploration and generalizability across JSP variants (details not available in the provided abstract).
Closest papers by meaning
- DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization (AAAI 2024 · similarity 0.86)
- Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies (NeurIPS 2026 · similarity 0.86)
- Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling (ICLR 2024 · similarity 0.86)
- Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling (NeurIPS 2025 · similarity 0.86)
- Going Beyond Heuristics by Imposing Policy Improvement as a Constraint (NeurIPS 2024 · similarity 0.86)
- Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
