RESEARCH

ML APPLICATIONS

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

November 10, 2020

Abstract

Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones -- and a generator's policy to produce trajectories that can fool this discriminator. This alternated optimization is known to be delicate in practice since it compounds unstable adversarial training with brittle and sample-inefficient reinforcement learning. We propose to remove the burden of the policy optimization steps by leveraging a novel discriminator formulation. Specifically, our discriminator is explicitly conditioned on two policies: the one from the previous generator's iteration and a learnable policy. When optimized, this discriminator directly learns the optimal generator's policy. Consequently, our discriminator's update solves the generator's optimization problem for free: learning a policy that imitates the expert does not require an additional optimization loop. This formulation effectively cuts by half the implementation and computational burden of Adversarial Imitation Learning algorithms by removing the Reinforcement Learning phase altogether. We show on a variety of tasks that our simpler approach is competitive to prevalent Imitation Learning methods.

Download the Paper

AUTHORS

Written by

Joelle Pineau

Christopher Pal

Derek Nowrouzezahrai

Julien Roy

Paul Barde

Wonseok Jeon

Publisher

NeurIPS

Related Publications

February 07, 2025

RESEARCH

SPEECH & AUDIO

Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound

Andros Tjandra, Yi-Chiao Wu, Baishan Guo, John Hoffman, Brian Ellis, Apoorv Vyas, Bowen Shi, Sanyuan Chen, Matt Le, Nick Zacharov, Carleigh Wood, Ann Lee, Wei-Ning Hsu

February 07, 2025

February 06, 2025

RESEARCH

NLP

Brain-to-Text Decoding: A Non-invasive Approach via Typing

Jarod Levy, Mingfang (Lucy) Zhang, Svetlana Pinet, Jérémy Rapin, Hubert Jacob Banville, Stéphane d'Ascoli, Jean Remi King

February 06, 2025

February 06, 2025

RESEARCH

NLP

From Thought to Action: How a Hierarchy of Neural Dynamics Supports Language Production

Mingfang (Lucy) Zhang, Jarod Levy, Stéphane d'Ascoli, Jérémy Rapin, F.-Xavier Alario, Pierre Bourdillon, Svetlana Pinet, Jean Remi King

February 06, 2025

November 28, 2022

RESEARCH

CORE MACHINE LEARNING

Neural Attentive Circuits

Nicolas Ballas, Bernhard Schölkopf, Chris Pal, Francesco Locatello, Li Erran, Martin Weiss, Nasim Rahaman, Yoshua Bengio

November 28, 2022

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.