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 301–350 of 2122 papers

TitleStatusHype
Spatially Visual Perception for End-to-End Robotic Learning—0
Self-reconfiguration Strategies for Space-distributed Spacecraft—0
LHPF: Look back the History and Plan for the Future in Autonomous Driving—0
RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations—0
End-to-End Steering for Autonomous Vehicles via Conditional Imitation Co-Learning—0
WildLMa: Long Horizon Loco-Manipulation in the Wild—0
Neuromorphic Attitude Estimation and ControlCode1
Instant Policy: In-Context Imitation Learning via Graph Diffusion—0
Error-Feedback Model for Output Correction in Bilateral Control-Based Imitation Learning—0
Bridging the Resource Gap: Deploying Advanced Imitation Learning Models onto Affordable Embedded Platforms—0
Learning Generalizable 3D Manipulation With 10 DemonstrationsCode0
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented ImitationCode0
Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment—0
Robot See, Robot Do: Imitation Reward for Noisy Financial Environments—0
Imitation Learning from Observations: An Autoregressive Mixture of Experts Approach—0
Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning—0
Learning Memory Mechanisms for Decision Making through DemonstrationsCode0
EMPERROR: A Flexible Generative Perception Error Model for Probing Self-Driving Planners—0
Identifying Differential Patient Care Through Inverse Intent Inference—0
Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration—0
Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion InversionCode1
IGDrivSim: A Benchmark for the Imitation Gap in Autonomous DrivingCode1
Scaling Laws for Pre-training Agents and World Models—0
ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy—0
Object and Contact Point Tracking in Demonstrations Using 3D Gaussian Splatting—0
Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning—0
Efficient Active Imitation Learning with Random Network Distillation—0
So You Think You Can Scale Up Autonomous Robot Data Collection?—0
GarmentLab: A Unified Simulation and Benchmark for Garment ManipulationCode2
Safe Imitation Learning-based Optimal Energy Storage Systems Dispatch in Distribution Networks—0
State- and context-dependent robotic manipulation and grasping via uncertainty-aware imitation learning—0
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task AlignmentCode0
EgoMimic: Scaling Imitation Learning via Egocentric VideoCode2
DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning—0
3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing—0
SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving—0
Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation—0
Keypoint Abstraction using Large Models for Object-Relative Imitation Learning—0
Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning—0
Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding—0
Identifying Selections for Unsupervised Subtask Discovery—0
Unveiling the Role of Expert Guidance: A Comparative Analysis of User-centered Imitation Learning and Traditional Reinforcement Learning—0
GHIL-Glue: Hierarchical Control with Filtered Subgoal Images—0
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and OptimizationCode2
MILES: Making Imitation Learning Easy with Self-Supervision—0
SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment—0
SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation—0
Reinforced Imitative Trajectory Planning for Urban Automated DrivingCode1
Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning—0
Reward-free World Models for Online Imitation LearningCode1
Show:102550
← PrevPage 7 of 43Next →

No leaderboard results yet.