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 1776–1800 of 2122 papers

TitleStatusHype
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation—0
Reinforced Imitation in Heterogeneous Action Space—0
Reinforced Imitation Learning by Free Energy Principle—0
Reinforced Imitation Learning from Observations—0
Reinforcement and Imitation Learning via Interactive No-Regret Learning—0
Reinforcement Learning for Battery Energy Storage Dispatch augmented with Model-based Optimizer—0
Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning—0
Reinforcement Learning via Implicit Imitation Guidance—0
Reinforcement Learning without Human Feedback for Last Mile Fine-Tuning of Large Language Models—0
Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal RepresentationsCode0
Task-Embedded Control Networks for Few-Shot Imitation LearningCode0
Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation LearningCode0
Autoregressive Knowledge Distillation through Imitation LearningCode0
Task-Oriented Hand Motion Retargeting for Dexterous Manipulation ImitationCode0
A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based ModelsCode0
Sequence Model Imitation Learning with Unobserved ContextsCode0
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to ImitationCode0
Follow the Neurally-Perturbed Leader for Adversarial TrainingCode0
Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium ProofCode0
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task AlignmentCode0
SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement LearningCode0
Transfer Learning for Prosthetics Using Imitation LearningCode0
CARLA: An Open Urban Driving SimulatorCode0
One-Shot Visual Imitation Learning via Meta-LearningCode0
Learning Calibratable Policies using Programmatic Style-ConsistencyCode0
Show:102550
← PrevPage 72 of 85Next →

No leaderboard results yet.