Research map / Reinforcement learning / Policy gradient and actor-critic
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Alois Knoll, Ming Jin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use CR-MOPO instead of LP3 | Walker-dm · Safe Multi-Objective Walker-dm (cost limit 1.5) | move reward: 250 -> 800 | Improved |
| use CR-MOPO instead of LP3 | Walker-dm · Safe Multi-Objective Walker-dm (cost limit 1.5) | height reward: 800 -> 600 | Hurt |
| use CR-MOPO instead of LP3 | Humanoid-dm · Safe Multi-Objective Humanoid-dm (cost limit 1.5) | move forward reward: 300 -> 600 | Improved |
| use CR-MOPO instead of LP3 | Humanoid-dm · Safe Multi-Objective Humanoid-dm (cost limit 1.5) | move left reward: 400 -> 400 | No clear effect |
| use CR-MOPO or CR-MOPO-S instead of CRPO | Safe Multi-Objective HalfCheetah (cost limit 0.005) · Safe Multi-Objective HalfCheetah (cost limit 0.005) | reward and safety | Improved |
Closest papers by meaning
- Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning (ICLR 2025 · similarity 0.92)
- An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning (NeurIPS 2024 · similarity 0.92)
- Feasible Policy Optimization for Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.92)
- SafeMPO: Constrained Reinforcement Learning with Probabilistic Incremental Improvement (ICLR 2026 · similarity 0.91)
- Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation (AAAI 2024 · similarity 0.90)
- Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation (ICML 2024 · similarity 0.89)
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.
