AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Proximal Point Imitation Learning

Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher

NeurIPS 2022 · Reinforcement learning › Imitation learning · approach: Offline imitation from imperfect data · 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 P2IL (proximal point) instead of GAIL, AIRL and IQ-Learn in tabular online ILP2IL · tabular environments (online)total returnImproved
use P2IL with neural network function approximation instead of IQ-LearnP2IL · CartPole and Acrobot (online)total returnHurt
use P2IL (dual smoothing) instead of IQ-Learn and AVRIL for offline ILP2IL offline · offline IL benchmarkstotal returnNo clear effect
run P2IL with image-based observations and neural costP2IL · Pong (Atari)total returnImproved
approximate the policy improvement step with SAC for continuous actionsP2IL · MuJoCo Ant, HalfCheetah, Hopper, Walkertotal returnImproved
transfer the recovered cost to a Gridworld with swapped action effects instead of using the imitating policyP2IL recovered cost · Gridworld cost transfervalue function / optimality under new dynamicsImproved

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