AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Model Predictive Adversarial Imitation Learning for Planning from Observation

Tyler Han, Yanda Bao, Bhaumik Mehta, Gabriel Guo, Sanghun Jung, Anubhav Vishwakarma, Emily Kang, Rosario Scalise, Jason Liren Zhou, Bryan Xu, Byron Boots

ICLR 2026 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models

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 changedWhereMeasuredEffect
deploy the learned reward through an MPPI planner instead of a policy (IRL-MPC vs GAIL) (ablation)GAIL reward and value · Real-Sim-Real navigationmean cross-track error (m): 0.56 -> 0.37Improved
train reward and value end to end with the online planner (MPAIL vs IRL-MPC) (ablation)IRL-MPC · Real-Sim-Real navigationmean cross-track error (m): 0.37 -> 0.17Improved
replace the AIL policy with an online MPPI plannerGAIL · simulated navigation, out-of-distribution initial poses (40x40 m)final rewardImproved
replace the AIL policy with an online MPPI plannerGAIL · simulated navigation task, interaction efficiencyinteractions to optimalityImproved
learn the dynamics model online (MPAIL OM) instead of using an approximate prior model (ablation)MPAIL · simulated cartpole tasksample efficiencyHurt
use MPAIL with a learned dynamics model instead of a policy network (ablation)GAIL and BC · OOD navigation evaluationfinal rewardImproved
increase MPPI iterations from 2 to 5 at horizon H=10 (ablation)MPAIL · navigation wall clock time vs GAILrelative training time: about 10% faster than GAIL -> about 10% slowerHurt
use discount factor eta below 1 on costs in MPPI horizon (ablation)MPAIL · simulated navigation taskconvergenceHurt
add temperature decay to MPPI (ablation)MPAIL · simulated navigation tasktraining stabilityImproved
use AIRL reward instead of GAILpolicy-based AIL · simulated navigation task (multimodal expert data)convergenceHurt

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