Research map / Reinforcement learning / Imitation learning
Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Choose demonstrations while accounting for learner preferences instead of ignoring them | Learner IRL in object-world environments, L1 · 10×10 object-worlds, L1 | average reward: 7.99\pm 0.02 -> 8.00 \pm 0.02 | No clear effect |
| Choose demonstrations while accounting for learner preferences instead of ignoring them | Learner IRL in object-world environments, L2 · 10×10 object-worlds, L2 | average reward: 0.01 \pm 0.00 -> 7.20 \pm 0.01 | Helped |
| Choose demonstrations while accounting for learner preferences instead of ignoring them | Learner IRL in object-world environments, L3 · 10×10 object-worlds, L3 | average reward: 0.01 \pm 0.00 -> 4.86 \pm 0.30 | Helped |
| Choose demonstrations while accounting for learner preferences instead of ignoring them | Learner IRL in object-world environments, L4 · 10×10 object-worlds, L4 | average reward: 0.01 \pm 0.00 -> 3.15 \pm 0.27 | Helped |
| Choose demonstrations while accounting for learner preferences instead of ignoring them | Learner IRL in object-world environments, L5 · 10×10 object-worlds, L5 | average reward: 0.00 \pm 0.00 -> 1.30 \pm 0.07 | Helped |
| Use adaptive teaching that updates demonstrations based on the learner's observed feature expectations | AdAware-Vol and AdAware-Lin · Object-world environments with unknown constraints | learner reward | Helped |
| Continue teaching with AdAware-Vol beyond the third round | AdAware-Vol · Object-world environments with unknown constraints | learner reward | Hurt |
Closest papers by meaning
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.89)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.88)
- Inverse Reinforcement Learning by Estimating Expertise of Demonstrators (AAAI 2025 · similarity 0.88)
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.88)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 2024 · similarity 0.87)
- Learning Utilities from Demonstrations in Markov Decision Processes (ICML 2025 · similarity 0.87)
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.