AdversarialSoftAdvantageFitting: ImitationLearningwithoutPolicyOptimization

Feb-9-2026, 08:37:00 GMT–Neural Information Processing Systems

When optimized, this discriminator directly learns the optimal generator'spolicy.

artificial intelligence, machine learning, reinforcement learning, (16 more...)

Neural Information Processing Systems

Feb-9-2026, 08:37:00 GMT

Conferences PDF

Country:
- North America > Canada
  - Quebec > Montreal (0.04)
  - British Columbia > Metro Vancouver Regional District
    - Vancouver (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.32)

Duplicate Docs Excel Report

Title
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization Paul Barde

Similar Docs Excel Report more

Title	Similarity	Source
None found