Research map / Bandits and online learning / RL theory and MDPs
Online Apprenticeship Learning
Lior Shani, Tom Zahavy, Shie Mannor
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 optimistic UCB bonuses for exploration (ablation) | OAL · Tabular MDP | AL regret | Improved |
| Initialize the transition model from expert trajectories (ablation) | OAL · Tabular MDP | AL regret | No clear effect |
| Add OAL to behavioral cloning initialization (ablation) | OAL · Online imitation learning | online regret | Improved |
| Use linear costs instead of neural costs (ablation) | OAL · MuJoCo continuous control tasks | imitation performance | No clear effect |
| Replace the GAIL discriminator objective with direct OAL cost optimization | OAL versus GAIL · MuJoCo continuous control tasks | imitation performance | Improved |
| Use off-policy MDPO instead of on-policy TRPO (ablation) | OAL and GAIL · MuJoCo continuous control tasks | imitation performance | Improved |
| Enforce Lipschitz regularization on learned costs (ablation) | OAL · HalfCheetah-v3 | imitation performance | Improved |
Closest papers by meaning
- Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data (AAAI 2025 · similarity 0.85)
- RLIF: Interactive Imitation Learning as Reinforcement Learning (ICLR 2024 · similarity 0.85)
- Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback (NeurIPS 2026 · similarity 0.84)
- Robust Policy Learning via Offline Skill Diffusion (AAAI 2024 · similarity 0.84)
- Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity (NeurIPS 2024 · similarity 0.84)
- Reward-free World Models for Online Imitation Learning (ICML 2025 · similarity 0.84)
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.
