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 1421–1430 of 2122 papers

TitleStatusHype
Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness—0
ReAgent: Point Cloud Registration using Imitation and Reinforcement LearningCode1
Co-Imitation Learning without Expert Demonstration—0
Imitation Learning from MPC for Quadrupedal Multi-Gait Control—0
Self-Imitation Learning by Planning—0
Adversarial Imitation Learning with Trajectorial Augmentation and CorrectionCode0
On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions—0
Learning 6DoF Grasping Using Reward-Consistent Demonstration—0
Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks—0
Online Baum-Welch algorithm for Hierarchical Imitation LearningCode0
Show:102550
← PrevPage 143 of 213Next →

No leaderboard results yet.