AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees

Siliang Zeng, Chenliang Li, Alfredo Garcia, Mingyi Hong

NeurIPS 2022 · Reinforcement learning › Imitation learning · approach: Theory of inverse RL · 4 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 ML-IRL (State-Only) instead of f-IRLML-IRL · MuJoCo Hoppercumulative reward: 3074.55 -> 3089.79Improved
Use ML-IRL (State-Action) instead of f-IRLML-IRL · MuJoCo Antcumulative reward: 4571.71 -> 4984.34Improved
Use ML-IRL (State-Action) instead of f-IRLML-IRL · MuJoCo Half-Cheetahcumulative reward: 4375.88 -> 4086.92Hurt
Use ML-IRL (State-Only) instead of f-IRLML-IRL · MuJoCo Walkercumulative reward: 4464.20 -> 4380.17No clear effect
Use ML-IRL (State-Only) instead of f-IRLML-IRL · MuJoCo Humanoidcumulative reward: 5243.90 -> 5390.31Improved
Use imitation learning BC instead of IRL under a single expert trajectoryBC · MuJoCo Hoppercumulative reward: 20.49 vs 3089.79Hurt
Use ML-IRL (State-Only) instead of f-IRL in data transferML-IRL · Custom-Ant to Disabled-Ant data transferscore: 188.85 -> 221.51Improved
Use ML-IRL (State-Only) instead of f-IRL in reward transferML-IRL · Custom-Ant to Disabled-Ant reward transferscore: 156.45 -> 187.69Improved
Use IQ-Learn instead of f-IRL in transferIQ-Learn · Custom-Ant to Disabled-Ant data transferscore: 188.85 -> -11.78Hurt
Use state-only reward instead of state-action rewardML-IRL · MuJoCo Humanoidcumulative reward: 5390.31 -> 5240.57Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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