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 201–250 of 2122 papers

TitleStatusHype
Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze and Bottleneck—0
GOD model: Privacy Preserved AI School for Personal AssistantCode0
Hierarchical Imitation Learning of Team Behavior from Heterogeneous Demonstrations—0
Towards a Reward-Free Reinforcement Learning Framework for Vehicle Control—0
BOSS: Benchmark for Observation Space Shift in Long-Horizon Task—0
VaViM and VaVAM: Autonomous Driving through Video Generative ModelingCode2
Making Universal Policies UniversalCode0
Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning—0
ModSkill: Physical Character Skill Modularization—0
A Training-Free Framework for Precise Mobile Manipulation of Small Everyday Objects—0
MILE: Model-based Intervention Learning—0
Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex TasksCode0
Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal TransportCode1
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification—0
HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit—0
RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning—0
Towards Fusing Point Cloud and Visual Representations for Imitation Learning—0
IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation—0
X-IL: Exploring the Design Space of Imitation Learning PoliciesCode2
FitLight: Federated Imitation Learning for Plug-and-Play Autonomous Traffic Signal Control—0
FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation—0
AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning—0
Object-Centric Latent Action Learning—0
DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human ReferencesCode2
CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World—0
Imit Diff: Semantics Guided Diffusion Transformer with Dual Resolution Fusion for Imitation Learning—0
A Unifying Framework for Causal Imitation Learning with Hidden Confounders—0
Predictive Red Teaming: Breaking Policies Without Breaking Robots—0
Imitation Learning from a Single Temporally Misaligned VideoCode0
Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs—0
DexterityGen: Foundation Controller for Unprecedented Dexterity—0
Action-Free Reasoning for Policy Generalization—0
OmniRL: In-Context Reinforcement Learning by Large-Scale Meta-Training in Randomized Worlds—0
RoboGrasp: A Universal Grasping Policy for Robust Robotic Control—0
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation—0
VILP: Imitation Learning with Latent Video PlanningCode1
Coarse-to-Fine 3D Keyframe Transporter—0
End-to-End Imitation Learning for Optimal Asteroid Proximity Operations—0
Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied AgentsCode0
EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World—0
DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems—0
Diffusion-Based Planning for Autonomous Driving with Flexible GuidanceCode4
Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation—0
SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation—0
Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Tasks—0
You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations—0
ACT-JEPA: Joint-Embedding Predictive Architecture Improves Policy Representation Learning—0
Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingCode2
Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning—0
Diffusion-Based Imitation Learning for Social Pose Generation—0
Show:102550
← PrevPage 5 of 43Next →

No leaderboard results yet.