Generative Adversarial Imitation Learning

Introduced by Ho et al. in Generative Adversarial Imitation Learning

Generative Adversarial Imitation Learning presents a new general framework for directly extracting a policy from data, as if it were obtained by reinforcement learning following inverse reinforcement learning.

Source: Generative Adversarial Imitation Learning

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Imitation Learning	37	43.02%
Reinforcement Learning (RL)	13	15.12%
Reinforcement Learning	8	9.30%
Continuous Control	5	5.81%
Autonomous Vehicles	2	2.33%
Autonomous Driving	2	2.33%
Autonomous Navigation	2	2.33%
Diversity	1	1.16%
Federated Learning	1	1.16%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Adversarial Training