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 851–875 of 2122 papers

TitleStatusHype
CALM: Conditional Adversarial Latent Models for Directable Virtual Characters—0
A Coupled Flow Approach to Imitation LearningCode1
Learning Environment for the Air Domain (LEAD)—0
Learning to Extrapolate: A Transductive ApproachCode1
Distance Weighted Supervised Learning for Offline Interaction DataCode0
Programmatically Grounded, Compositionally Generalizable Robotic Manipulation—0
Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approach—0
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware—0
Self-Supervised Adversarial Imitation LearningCode1
Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive ImitationCode0
Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated EnvironmentsCode0
Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets—0
Reward-free Policy Imitation Learning for Conversational Search—0
MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed—0
Affordances from Human Videos as a Versatile Representation for Robotics—0
Synthetically Generating Human-like Data for Sequential Decision Making Tasks via Reward-Shaped Imitation Learning—0
Car-Following Models: A Multidisciplinary Review—0
Curriculum-Based Imitation of Versatile SkillsCode0
For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal—0
Learning Robot Manipulation from Cross-Morphology DemonstrationCode0
CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning—0
End-to-end Manipulator Calligraphy Planning via Variational Imitation Learning—0
Goal-Conditioned Imitation Learning using Score-based Diffusion PoliciesCode1
ENTL: Embodied Navigation Trajectory Learner—0
Quantum Imitation Learning—0
Show:102550
← PrevPage 35 of 85Next →

No leaderboard results yet.