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 501–550 of 2122 papers

TitleStatusHype
Data-Efficient Learning from Human Interventions for Mobile Robots—0
Enhancing Autonomous Driving Safety with Collision Scenario Integration—0
Curating Demonstrations using Online Experience—0
ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation—0
A2Perf: Real-World Autonomous Agents Benchmark—0
Perceptual Motor Learning with Active Inference Framework for Robust Lateral Control—0
FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interaction—0
Improving Retrospective Language Agents via Joint Policy Gradient Optimization—0
CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving—0
CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous DrivingCode0
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping—0
ProDapt: Proprioceptive Adaptation using Long-term Memory DiffusionCode0
RIZE: Regularized Imitation Learning via Distributional Reinforcement LearningCode0
IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic—0
ObjectVLA: End-to-End Open-World Object Manipulation Without Demonstration—0
Task-Driven Semantic Quantization and Imitation Learning for Goal-Oriented Communications—0
Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze and Bottleneck—0
Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations—0
GOD model: Privacy Preserved AI School for Personal AssistantCode0
BOSS: Benchmark for Observation Space Shift in Long-Horizon Task—0
Towards a Reward-Free Reinforcement Learning Framework for Vehicle Control—0
Making Universal Policies UniversalCode0
Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning—0
MILE: Model-based Intervention Learning—0
A Training-Free Framework for Precise Mobile Manipulation of Small Everyday Objects—0
ModSkill: Physical Character Skill Modularization—0
RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning—0
HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit—0
Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex TasksCode0
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification—0
IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation—0
Towards Fusing Point Cloud and Visual Representations for Imitation Learning—0
FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation—0
FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control—0
AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning—0
Object-Centric Latent Action Learning—0
CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World—0
A Unifying Framework for Causal Imitation Learning with Hidden Confounders—0
Imit Diff: Semantics Guided Diffusion Transformer with Dual Resolution Fusion for Imitation Learning—0
Predictive Red Teaming: Breaking Policies Without Breaking Robots—0
Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs—0
Imitation Learning from a Single Temporally Misaligned VideoCode0
DexterityGen: Foundation Controller for Unprecedented Dexterity—0
Action-Free Reasoning for Policy Generalization—0
RoboGrasp: A Universal Grasping Policy for Robust Robotic Control—0
OmniRL: In-Context Reinforcement Learning by Large-Scale Meta-Training in Randomized Worlds—0
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation—0
End-to-End Imitation Learning for Optimal Asteroid Proximity Operations—0
Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied AgentsCode0
Coarse-to-Fine 3D Keyframe Transporter—0
Show:102550
← PrevPage 11 of 43Next →

No leaderboard results yet.