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 351–400 of 2122 papers

TitleStatusHype
Latent Weight Diffusion: Generating reactive policies instead of trajectories—0
Diffusing States and Matching Scores: A New Framework for Imitation LearningCode1
DDIL: Diversity Enhancing Diffusion Distillation With Imitation Learning—0
ILAEDA: An Imitation Learning Based Approach for Automatic Exploratory Data Analysis—0
DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action AlignmentCode1
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning PerspectiveCode0
Zero-Shot Offline Imitation Learning via Optimal TransportCode1
Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback—0
ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback—0
Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman ControllersCode0
UNIQ: Offline Inverse Q-learning for Avoiding Undesirable DemonstrationsCode0
Mastering Contact-rich Tasks by Combining Soft and Rigid Robotics with Imitation Learning—0
FürElise: Capturing and Physically Synthesizing Hand Motions of Piano Performance—0
Quality Diversity Imitation Learning—0
Diffusion Imitation from Observation—0
Active Multi-task Policy Fine-tuningCode0
HE-Drive: Human-Like End-to-End Driving with Vision Language Models—0
On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning—0
Online Control-Informed Learning—0
Robust Offline Imitation Learning from Diverse Auxiliary Data—0
Latent Action Priors for Locomotion with Deep Reinforcement Learning—0
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and ObjectsCode1
SEAL: SEmantic-Augmented Imitation Learning via Language Model—0
ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AICode1
Effective Tuning Strategies for Generalist Robot Manipulation Policies—0
CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction—0
Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control—0
Learning to Build by Building Your Own InstructionsCode0
ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AICode7
M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning—0
Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning—0
Learning Strategy Representation for Imitation Learning in Multi-Agent Games—0
Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning—0
Good Data Is All Imitation Learning Needs—0
Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models—0
Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous DrivingCode2
Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance—0
Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost—0
CANDERE-COACH: Reinforcement Learning from Noisy Feedback—0
RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning—0
Generalized Robot Learning Framework—0
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control—0
IMRL: Integrating Visual, Physical, Temporal, and Geometric Representations for Enhanced Food Acquisition—0
InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation—0
A Perspective on AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systems—0
Robot Utility Models: General Policies for Zero-Shot Deployment in New EnvironmentsCode3
Interactive incremental learning of generalizable skills with local trajectory modulationCode0
An Analysis of Logit Learning with the r-Lambert Function—0
The Prevalence of Neural Collapse in Neural Multivariate Regression—0
Hybrid Imitation-Learning Motion Planner for Urban Driving—0
Show:102550
← PrevPage 8 of 43Next →

No leaderboard results yet.