Research map / Reinforcement learning / Imitation learning
Misspecification in Inverse Reinforcement Learning
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 |
|---|---|---|---|
| Allow the Boltzmann-rational temperature to vary as a function of the reward | Boltzmann-rational IRL · General finite MDPs | ORD robustness to behavioral-model misspecification | Helped |
| Allow the causal entropy weight to vary as a function of the reward | Maximal causal entropy IRL · General finite MDPs | ORD robustness to behavioral-model misspecification | Helped |
| Use an optimality-only behavioral model | Optimality-based IRL · General finite MDPs | OPT robustness to behavioral-model misspecification | Hurt |
| Misspecify the transition function τ | Standard IRL behavioral models · Nontrivial transition functions | OPT robustness | Hurt |
| Misspecify the discount parameter γ | Standard IRL behavioral models · Nontrivial transition functions | OPT robustness | Hurt |
| Require the learned reward to preserve policy ordering rather than only optimal policies | Optimal-policy behavioral models · General finite MDPs | ORD admissibility | Hurt |
| Restrict rewards to a known subset of the full reward space | IRL robustness analysis · Restricted reward-function class | Robustness guarantees | Mixed |
Closest papers by meaning
- Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification (ICLR 2024 · similarity 0.97)
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting (AAAI 2025 · similarity 0.90)
- Efficient Imitation under Misspecification (ICLR 2025 · similarity 0.90)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.90)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 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.