AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Distributional Inverse Reinforcement Learning

Feiyang Wu, Ye Zhao, Anqi Wu

ICML 2026 · Reinforcement learning › Imitation learning · approach: Reward learning from demonstrations · 0 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 distributional reward with FSD loss instead of deterministic reward (Det-TD-Mean) (ablation)DistIRL · HalfCheetah ablationscaled performance: 0.22 -> 1.00Improved
use FSD loss instead of mean matching with distributional reward and quantile critic (ablation)DistIRL · HalfCheetah ablationscaled performance: 0.22 -> 1.00Improved
use distributional reward instead of deterministic reward with quantile critic and mean matching (ablation)Qt-Mean · HalfCheetah ablationscaled performance: 0.00 -> 0.22Improved
use FSD loss instead of mean matching with TD critic (ablation)Dis-TD · HalfCheetah ablationscaled performance: 0.33 -> 0.67Improved
use quantile critic instead of TD critic with FSD loss (ablation)DistIRL · HalfCheetah ablationscaled performance: 0.67 -> 1.00Improved
use distributional reward IRL instead of offline baselines in risk-sensitive settingDistIRL · Risk-sensitive D4RL HalfCheetahreturn: 1259 -> 3469Improved
use DistIRL instead of BCDistIRL · Risk-sensitive D4RL Hopperreturn: 346 -> 886Improved
use Gaussian reward instead of quantile-function reward parameterizationDistIRL · Risk-sensitive D4RLreturn: 3294 -> 3469 on HalfCheetahMixed
use DistIRL instead of Offline ML-IRL in risk-neutral settingDistIRL · Risk-neutral D4RL HalfCheetahreturn: 11231 -> 7779Hurt
use DistIRL instead of Offline ML-IRL in risk-neutral settingDistIRL · Risk-neutral D4RL Walker2dreturn: 4201 -> 4570Improved
use skew-normal reward model instead of GaussianDistIRL · dopamine trackingcorrelation / W-1Improved
change distortion risk measure to one far from expert risk preference (ablation)DistIRL · D4RL appendixreturnHurt

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