SOTAVerified

Imitation Learning

Imitation Learning is a framework for learning a behavior policy from demonstrations. Usually, demonstrations are presented in the form of state-action trajectories, with each pair indicating the action to take at the state being visited. In order to learn the behavior policy, the demonstrated actions are usually utilized in two ways. The first, known as Behavior Cloning (BC), treats the action as the target label for each state, and then learns a generalized mapping from states to actions in a supervised manner. Another way, known as Inverse Reinforcement Learning (IRL), views the demonstrated actions as a sequence of decisions, and aims at finding a reward/cost function under which the demonstrated decisions are optimal.

Finally, a newer methodology, Inverse Q-Learning aims at directly learning Q-functions from expert data, implicitly representing rewards, under which the optimal policy can be given as a Boltzmann distribution similar to soft Q-learning

Source: Learning to Imitate

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1051–1060 of 2122 papers

TitleStatusHype
End-to-End Imitation Learning for Optimal Asteroid Proximity Operations—0
CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation—0
Adversarial Exploration Strategy for Self-Supervised Imitation Learning—0
Learning Dynamic Graph for Overtaking Strategy in Autonomous Driving—0
End-to-End Driving via Self-Supervised Imitation Learning Using Camera and LiDAR Data—0
End-to-end driving simulation via angle branched network—0
CEIL: Generalized Contextual Imitation Learning—0
A Bayesian Approach to Generative Adversarial Imitation Learning—0
Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future—0
Learning Efficient Planning-based Rewards for Imitation Learning—0
Show:102550
← PrevPage 106 of 213Next →

No leaderboard results yet.