Research map / Reinforcement learning / Policy gradient and actor-critic
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
Runzhe Yang, Xingyuan Sun, Karthik Narasimhan
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 envelope updates instead of scalarized updates | Deep MORL · DST | CR: 0.989 $\pm$ 0.024 -> 0.994 $\pm$ 0.001 | Improved |
| Use envelope updates instead of scalarized updates | Deep MORL · DST | AE: 0.165 $\pm$ 0.096 -> 0.152 $\pm$ 0.006 | Improved |
| Use envelope updates instead of scalarized updates | Deep MORL · FTN (d=6) | CR: 0.914 $\pm$ 0.044 -> 0.987 $\pm$ 0.021 | Improved |
| Use envelope updates instead of scalarized updates | Deep MORL · FTN (d=6) | AE: 0.016 $\pm$ 0.005 -> 0.006 $\pm$ 0.001 | Improved |
| Use envelope updates instead of scalarized updates | Deep MORL · Dialog | Avg. UT: 2.38 $\pm$ 0.22 -> 2.65 $\pm$ 0.22 | Improved |
| Use envelope updates instead of scalarized updates | Deep MORL · SuperMario | Avg. UT: 162.7 $\pm$ 77.66 -> 321.2 $\pm$ 146.9 | Improved |
| Increase the number of sampled preferences | Envelope and scalarized deep MORL · FTN tasks at depths d=5, d=6, d=7 | CR | Improved |
| Use envelope updates rather than scalarized updates | Deep MORL · FTN tasks at depths d=5, d=6, d=7 | CR | Improved |
Closest papers by meaning
- Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization (NeurIPS 2026 · similarity 0.92)
- An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- On Generalization Across Environments In Multi-Objective Reinforcement Learning (ICLR 2025 · similarity 0.90)
- Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach (NeurIPS 2025 · similarity 0.90)
- Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization (ICML 2025 · similarity 0.90)
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.
