Research map / Reinforcement learning / Imitation learning
Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
Luca Viano, Yu-Ting Huang, Parameswaran Kamalaruban, Adrian Weller, 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 |
|---|---|---|---|
| add robust MCE IRL (two-player Markov game, alpha<1) instead of standard MCE IRL | MCE IRL · GridWorld / ObjectWorld under expert-learner dynamics mismatch | learner return V under learner MDP | Improved |
| add robust training (alpha<1) in the low expert-noise regime (little mismatch) | MCE IRL · GridWorld / ObjectWorld, low expert noise | learner return V under learner MDP | Hurt |
| underestimate opponent strength 1-alpha relative to true mismatch (ablation) | Robust MCE IRL · GridWorld / ObjectWorld | learner return V | Hurt |
| overestimate opponent strength 1-alpha relative to true mismatch (ablation) | Robust MCE IRL · GridWorld / ObjectWorld | learner return V | Hurt |
| set 1-alpha approx d_dyn(T^L, estimated T^E)/2 using a rough estimate of expert dynamics (ablation) | Robust MCE IRL · GridWorld / ObjectWorld | learner return V | Improved |
| add robust RE IRL (robust variant of Relative Entropy IRL) in continuous MDP | RE IRL · GaussianGrid | learner return | Improved |
| add robust MCE IRL with low-dimensional feature map | MCE IRL · low-dimensional feature GridWorld (Appendix) | learner return | Improved |
| choose alpha = 1 - d_dyn/2 in constructive example | Robust MCE IRL · three-state constructive MDP (theory) | performance gap to no-mismatch MCE IRL: gamma/(1-gamma) * d_dyn -> 0 | Improved |
Closest papers by meaning
- Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.89)
- State Entropy Regularization for Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Robust Inverse Constrained Reinforcement Learning under Model Misspecification (ICML 2024 · similarity 0.88)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.88)
- Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms (ICML 2024 · 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.
