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 391–400 of 2122 papers

TitleStatusHype
Adaptive Adversarial Imitation Learning—0
Behavior-Targeted Attack on Reinforcement Learning with Limited Access to Victim's Policy—0
Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets—0
Towards Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning—0
Amortized nonmyopic active search via deep imitation learning—0
Behavioral Cloning via Search in Video PreTraining Latent Space—0
Error-based or target-based? A unifying framework for learning in recurrent spiking networks—0
Amortized Noisy Channel Neural Machine Translation—0
Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence—0
VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections—0
Show:102550
← PrevPage 40 of 213Next →

No leaderboard results yet.