Research map / Reinforcement learning / Imitation learning
Teaching Inverse Reinforcement Learners via Features and Demonstrations
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 |
|---|---|---|---|
| select teachable features by greedily minimizing teaching risk instead of selecting them randomly | TRGreedy feature teaching · Gridworlds (N=20, n=2) | relative performance | Helped |
| select teachable features by greedily maximizing next-round performance rather than minimizing teaching risk | TRGreedy feature teaching · Gridworlds (N=20, n=2) | relative performance | Mixed |
| use greedy teaching-risk reduction instead of random feature selection | TRGreedy feature teaching · Gridworlds (N=20, n=2) | teaching risk | Helped |
| increase the learner's worldview teaching risk | Learner matching teacher feature expectations · Gridworlds (N=20, n=2) | variance of relative performance | Hurt |
| increase the discount factor | Learner matching teacher feature expectations · Gridworlds (N=20, n=2) | relative performance | Helped |
Closest papers by meaning
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.90)
- Learning Utilities from Demonstrations in Markov Decision Processes (ICML 2025 · similarity 0.90)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.90)
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Environment Design for Inverse Reinforcement Learning (ICML 2024 · similarity 0.89)
- Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning (NeurIPS 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.