AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Model-Free IRL Using Maximum Likelihood Estimation

Vinamra Jain, Prashant Doshi, Bikramjit Banerjee

AAAI 2019 · Reinforcement learning › Imitation learning · approach: Theory of inverse RL · 17 citations (OpenAlex)

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
use Q-averaging model-free Q update instead of model-based transitionsMLIRL · Gridworld no noisefinal log-likelihood: −36.50 ± 3.12 -> −29.25 ± 6.59Improved
use Q-averaging model-free Q update instead of model-based transitionsMLIRL · Gridworld 10% noisefinal log-likelihood: −45.05 ± 9.07 -> −40.49 ± 0.04Improved
use Q-averaging instead of model-based MLIRL with estimated transitionsMLIRL · Freeway merging NGSIMfinal log-likelihood: −1927.09 ± 1.1 -> −1891.34 ± 0.79Improved
replace max in Q-learning with Boltzmann-weighted mean (Q-softmax) instead of averaging (ablation)Q-averaging MLIRL · Gridworld no noisefinal log-likelihood: −29.25 ± 6.59 -> −40.39 ± 4.15Hurt
replace averaging with Boltzmann-weighted mean (Q-softmax) (ablation)Q-averaging MLIRL · Gridworld 10% noisefinal log-likelihood: −40.49 ± 0.04 -> −57.35 ± 0.30Hurt
replace averaging with Boltzmann-weighted mean (Q-softmax) (ablation)Q-averaging MLIRL · Freeway merging NGSIMfinal log-likelihood: −1891.34 ± 0.79 -> −1914.56 ± 1.38Hurt
use Q-softmax instead of model-based MLIRLMLIRL · Gridworld no noisefinal log-likelihood: −36.50 ± 3.12 -> −40.39 ± 4.15Hurt
use Q-softmax instead of model-based MLIRLMLIRL · Freeway merging NGSIMfinal log-likelihood: −1927.09 ± 1.1 -> −1914.56 ± 1.38Improved
use Q-averaging instead of REIRL (needs baseline trajectories)REIRL · Freeway merging NGSIMfinal log-likelihood: −1920.48 ± 3.24 -> −1891.34 ± 0.79Improved

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