AI Paper Atlas

Research map / Bandits and online learning / RL theory and MDPs

Online Apprenticeship Learning

Lior Shani, Tom Zahavy, Shie Mannor

AAAI 2022 · Bandits and online learning › RL theory and MDPs · approach: Non-stationary and structured MDPs · 9 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
Add optimistic UCB bonuses for exploration (ablation)OAL · Tabular MDPAL regretImproved
Initialize the transition model from expert trajectories (ablation)OAL · Tabular MDPAL regretNo clear effect
Add OAL to behavioral cloning initialization (ablation)OAL · Online imitation learningonline regretImproved
Use linear costs instead of neural costs (ablation)OAL · MuJoCo continuous control tasksimitation performanceNo clear effect
Replace the GAIL discriminator objective with direct OAL cost optimizationOAL versus GAIL · MuJoCo continuous control tasksimitation performanceImproved
Use off-policy MDPO instead of on-policy TRPO (ablation)OAL and GAIL · MuJoCo continuous control tasksimitation performanceImproved
Enforce Lipschitz regularization on learned costs (ablation)OAL · HalfCheetah-v3imitation performanceImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy