Research map / Reinforcement learning / Imitation learning
Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior
Brandon Araki, Kiran Vodrahalli, Thomas Leech, Cristian-Ioan Vasile, Mark Donahue, Daniela Rus
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 LVIN instead of LSTM baseline | LVIN · Lunchbox test | success rate: 82.44% -> 99.94% | Improved |
| use LVIN instead of LSTM baseline | LVIN · Cabinet test | success rate: 89.58% -> 100.0% | Improved |
| use LVIN instead of LSTM baseline | LVIN · Driving test | success rate: 58.60% -> 100.0% | Improved |
| use LVIN instead of LSTM baseline | LVIN · Lunchbox train | success rate: 91.44% -> 99.60% | Improved |
| use LVIN instead of LSTM baseline | LVIN · Cabinet train | success rate: 93.60% -> 100.00% | Improved |
| use LVIN instead of LSTM baseline | LVIN · Driving train | success rate: 58.54% -> 100.0% | Improved |
| use LVIN with far smaller training set | LVIN · Lunchbox | training set size: 500 vs 9000 | Improved |
| use LVIN with far smaller training set | LVIN · Driving | training set size: 500 vs 6000 | Improved |
| modify learned transition matrix to pick sandwich first (φl2) | LVIN · Jaco lunchbox | successes out of 20: 20 | No clear effect |
| modify learned transition matrix to pick banana first (φl4) | LVIN · Jaco lunchbox | successes out of 20: 19 | No clear effect |
| modify cabinet TM to get key before checking cabinet (φc2) | LVIN · Jaco cabinet | successes out of 20: 20 -> 17 | Mixed |
Closest papers by meaning
- Few-Shot Bayesian Imitation Learning with Logical Program Policies (AAAI 2020 · similarity 0.89)
- AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations (ICLR 2025 · similarity 0.89)
- Instant Policy: In-Context Imitation Learning via Graph Diffusion (ICLR 2025 · similarity 0.88)
- GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation (AAAI 2024 · similarity 0.87)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.87)
- Latent Diffusion Planning for Imitation Learning (ICML 2025 · 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.
