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 1051–1075 of 2122 papers

TitleStatusHype
Deep Reinforcement Learning-based Multi-objective Path Planning on the Off-road Terrain Environment for Ground Vehicles—0
Learning from Mistakes via Cooperative Study Assistant for Large Language ModelsCode0
End-to-End Stable Imitation Learning via Autonomous Neural Dynamic Policies—0
On the Correspondence between Compositionality and Imitation in Emergent Neural Communication—0
Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization—0
An Imitation Learning Based Algorithm Enabling Priori Knowledge Transfer in Modern Electricity Markets for Bayesian Nash Equilibrium Estimation—0
Scanpath Prediction in Panoramic Videos via Expected Code Length Minimization—0
Get Back Here: Robust Imitation by Return-to-Distribution Planning—0
CALM: Conditional Adversarial Latent Models for Directable Virtual Characters—0
Learning Environment for the Air Domain (LEAD)—0
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
Learning Representative Trajectories of Dynamical Systems via Domain-Adaptive ImitationCode0
Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets—0
Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated EnvironmentsCode0
Affordances from Human Videos as a Versatile Representation for Robotics—0
MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed—0
Reward-free Policy Imitation Learning for Conversational Search—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
CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning—0
Show:102550
← PrevPage 43 of 85Next →

No leaderboard results yet.