Research map / Reinforcement learning / Imitation learning
Task Transfer by Preference-Based Cost Learning
Mingxuan Jing, Xiaojian Ma, Wenbing Huang, Fuchun Sun, Huaping Liu
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 preference-based selection of related-task trajectories and iteratively learn the target distribution and cost | Preference-based task transfer · MountainCar: Two Peaks → One Peak | average return | Improved |
| Use preference-based selection of related-task trajectories and iteratively learn the target distribution and cost | Preference-based task transfer · Reacher: Two Targets → Center of Targets | average return | Improved |
| Use preference-based task transfer instead of requiring an accurate target cost | Preference-based task transfer · Half-Cheetah: Arbitrary → Backward | average cost on target task | No clear effect |
| Use preference-based task transfer instead of requiring an accurate target cost | Preference-based task transfer · Ant: Arbitrary → Single | average cost on target task | No clear effect |
| Learn trajectory distribution and cost with enhanced Adversarial MaxEnt IRL | Enhanced Adversarial MaxEnt IRL · Hopper, Walker2d, Humanoid, and Reacher | average cost | Improved |
| Initialize each iteration from the previous generator and discriminator rather than from scratch | Preference-based task transfer · Each transfer iteration | convergence speed | Improved |
| Add a selection constraint for stability | Preference-based task transfer · Transfer procedure | stability | Improved |
Closest papers by meaning
- PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation (ICML 2024 · similarity 0.89)
- Transfer Learning in Deep Reinforcement Learning: A Survey (TPAMI 2023 · similarity 0.88)
- Improving Reward Model Generalization from Adversarial Process Enhanced Preferences (ICML 2025 · similarity 0.87)
- Limited Preference Aided Imitation Learning from Imperfect Demonstrations (ICML 2024 · similarity 0.86)
- Predictive Preference Learning from Human Interventions (NeurIPS 2025 · similarity 0.86)
- Adaptive Preference Scaling for Reinforcement Learning with Human Feedback (NeurIPS 2024 · similarity 0.86)
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.
