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 101–150 of 2122 papers

TitleStatusHype
CIVIL: Causal and Intuitive Visual Imitation Learning—0
Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning—0
Integrating Learning-Based Manipulation and Physics-Based Locomotion for Whole-Body Badminton Robot Control—0
SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulation—0
Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline—0
A Model-Based Approach to Imitation Learning through Multi-Step Predictions—0
Imitation Learning with Precisely Labeled Human Demonstrations—0
Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration—0
Adapting a World Model for Trajectory Following in a 3D Game—0
Toward Aligning Human and Robot Actions via Multi-Modal Demonstration LearningCode0
Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge ModelsCode2
Improving In-Context Learning with Reasoning DistillationCode0
Diffusion Models for Robotic Manipulation: A Survey—0
AssistanceZero: Scalably Solving Assistance GamesCode2
CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous DrivingCode1
Stratified Expert Cloning with Adaptive Selection for User Retention in Large-Scale Recommender Systems—0
Tool-as-Interface: Learning Robot Policies from Human Tool Usage through Imitation Learning—0
Dexterous Manipulation through Imitation Learning: A Survey—0
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets—0
Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers—0
Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error—0
CBIL: Collective Behavior Imitation Learning for Fish from Real Videos—0
HACTS: a Human-As-Copilot Teleoperation System for Robot Learning—0
ZeroMimic: Distilling Robotic Manipulation Skills from Web VideosCode1
Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models—0
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models—0
Robust Offline Imitation Learning Through State-level Trajectory Stitching—0
Empirical Analysis of Sim-and-Real Cotraining Of Diffusion Policies For Planar Pushing from Pixels—0
Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning—0
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive TasksCode2
OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation—0
Bridging the Sim-to-real Gap: A Control Framework for Imitation Learning of Model Predictive Control—0
Bootstrapped Model Predictive ControlCode1
Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation—0
End-to-end Sketch-Guided Path Planning through Imitation Learning for Autonomous Mobile RobotsCode0
BEAC: Imitating Complex Exploration and Task-oriented Behaviors for Invisible Object Nonprehensile Manipulation—0
TamedPUMA: safe and stable imitation learning with geometric fabrics—0
Denoising-based Contractive Imitation LearningCode0
Learning 3D Scene Analogies with Neural Contextual Scene Maps—0
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse—0
RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints—0
StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion—0
Online Imitation Learning for Manipulation via Decaying Relative Correction through Teleoperation—0
Robotic Paper Wrapping by Learning Force Control—0
CCDP: Composition of Conditional Diffusion Policies with Guided Sampling—0
HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario GenerationCode1
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots—0
Learning Bimanual Manipulation via Action Chunking and Inter-Arm Coordination with Transformers—0
Quantization-Free Autoregressive Action TransformerCode0
Efficient Imitation under Misspecification—0
Show:102550
← PrevPage 3 of 43Next →

No leaderboard results yet.