Research map / Reinforcement learning / Imitation learning
An Empirical Investigation of Representation Learning for Imitation
Xin Chen, Sam Toyer, Cody Wild, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H Wang, Ping Luo, Stuart Russell, Pieter Abbeel, Rohin Shah
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 image augmentations to BC (ablation) | Behavioral Cloning · DMC finger-spin | return: 940±4* -> 730±9 | Hurt |
| Add image augmentations to BC (ablation) | Behavioral Cloning · DMC reacher-easy | return: 452±34 -> 874±21 | Improved |
| Add image augmentations to BC (ablation) | Behavioral Cloning · Procgen fruitbot-train | return: 11.4±0.6 -> 18.3±1.9 | Improved |
| Add image augmentations to BC (ablation) | Behavioral Cloning · MAGICAL MatchRegions | score: 0.28±0.08 -> 0.43±0.02 | Improved |
| Use representation learning pretraining instead of augmentation-only BC | BC across the evaluated benchmarks · DMC, Procgen, and MAGICAL | return | Mixed |
| Add joint representation learning as an auxiliary loss | BC on DMC · DMC | return | Improved |
| Add representation learning pretraining | BC on MAGICAL MoveToRegion · MAGICAL MoveToRegion | score: 0.74 -> 0.83 | Improved |
| Remove discriminator augmentations (ablation) | GAIL on DMC finger-spin · DMC finger-spin | return: 868±12 -> 0±0 | Hurt |
Closest papers by meaning
- Provable Representation Learning for Imitation Learning via Bi-level Optimization (ICML 2020 · similarity 0.90)
- Provable Representation Learning for Imitation with Contrastive Fourier Features (NeurIPS 2021 · similarity 0.90)
- Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction (ECCV 2022 · similarity 0.89)
- Robust Visual Imitation Learning with Inverse Dynamics Representations (AAAI 2024 · similarity 0.89)
- When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning (NeurIPS 2026 · similarity 0.88)
- OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning (ICML 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.
