Research map / Reinforcement learning / Imitation learning
MobILE: Model-Based Imitation Learning From Observation Alone
Rahul Kidambi, Jonathan Daniel Chang, Wen Sun
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 |
|---|---|---|---|
| Remove optimism from the optimistic MDP construction (ablation) | MobILE · MuJoCo suite | sample efficiency | Hurt |
| Increase expert trajectories from 5 to 10 (ablation) | MobILE · Cartpole-v1 | expert normalized score: 1.07\pm0.15 -> 1.14\pm0 | Improved |
| Increase expert trajectories from 10 to 20 (ablation) | MobILE · Reacher-v2 | expert normalized score: 1.01\pm0.05 -> 0.997\pm0.055 | No clear effect |
| Increase expert trajectories from 10 to 40 (ablation) | MobILE · Swimmer-v2 | expert normalized score: 1.54\pm1.1 -> 1.25\pm0.15 | Improved |
| Increase expert trajectories from 10 to 40 (ablation) | MobILE · Hopper-v2 | expert normalized score: 1.11\pm0.064 -> 1.16\pm0.03 | Improved |
| Increase expert trajectories from 10 to 50 (ablation) | MobILE · Walker2d-v2 | expert normalized score: 0.975\pm0.12 -> 0.94\pm0.038 | No clear effect |
| MobILE without expert actions versus BC and GAIL with actions | MobILE · MuJoCo suite | expert normalized score | No clear effect |
| MobILE versus ILFO baselines BC-O, ILPO, GAIFO | MobILE · MuJoCo suite | expert normalized score | Improved |
| MobILE versus BC under stochastic dynamics | MobILE · Stochastic Cartpole | task success | Improved |
Closest papers by meaning
- Imitation from Observations with Trajectory-Level Generative Embeddings (NeurIPS 2026 · similarity 0.89)
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning (NeurIPS 2025 · similarity 0.88)
- Imitation Learning from Observation with Automatic Discount Scheduling (ICLR 2024 · similarity 0.88)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.88)
- Zero-Shot Offline Imitation Learning via Optimal Transport (ICML 2025 · similarity 0.88)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (NeurIPS 2024 · similarity 0.88)
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.
