Research map / Reinforcement learning / Imitation learning
Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning
Paul Rolland, Luca Viano, Norman Schuerhoff, Boris Nikolov, Volkan Cevher
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 two experts in the randomly generated environments | IRL on Random-Matrices · Random-Matrices | reward identifiability up to a constant: rank 35 = 2|S| -1 = 35 | Improved |
| Use experts with different transition noise levels | IRL on Gridworld · Gridworld | reward identifiability up to a constant: α^1=0.4 and α^2=0.2 | Improved |
| Vary discount factors while keeping the transition dynamics fixed | IRL on Gridworld · Gridworld | reward identifiability up to a constant | Improved |
| Observe additional experts in environments with different wind distributions | IRL on WindyGridworld · WindyGridworld | generalizability: 4 experts | Improved |
| Use two experts in a setting with an exogenous productivity shock | IRL on Strebulaev-Whited · Strebulaev-Whited | reward identifiability up to a constant: 552 < 2|S| -1 = 799 | Hurt |
| Use the recovered reward to train in a third environment with σ_ε=0.6 | IRL on Strebulaev-Whited · Strebulaev-Whited | generalizability: σ_ε=0.6 | Improved |
| Restrict the reward to linear combinations of three known features | IRL on Strebulaev-Whited · Strebulaev-Whited | exact reward identifiability: 803 = 2|S| + d | Improved |
Closest papers by meaning
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.92)
- Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting (AAAI 2025 · similarity 0.91)
- Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.91)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 2024 · 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.
