Papers › Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

23 Jun 2020NeurIPS 2020 12arXiv:2006.13258archive 2025-07-28

Paul Barde, Julien Roy, Wonseok Jeon, Joelle Pineau, Christopher Pal, Derek Nowrouzezahrai

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ubisoft/ubisoft-la-forge-ASAF officialpytorchNOASSERTION report
leo27945875/ASAF-1 mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Imitation LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: ASAF, Adversarial Soft Advantage Fitting (ASAF)

Adversarial Soft Advantage Fitting (ASAF)GAIL

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections