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 51–100 of 2122 papers

TitleStatusHype
Inverse Q-Learning Done Right: Offline Imitation Learning in Q^π-Realizable MDPsCode0
ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous DrivingCode1
Structured Reinforcement Learning for Combinatorial Decision-MakingCode1
Online Knowledge Distillation with Reward Guidance—0
MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations—0
ProgRM: Build Better GUI Agents with Progress Rewards—0
Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy—0
Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space—0
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)—0
Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only—0
Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones—0
UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning—0
Guided Policy Optimization under Partial ObservabilityCode0
FLARE: Robot Learning with Implicit World Modeling—0
Learning-based Autonomous Oversteer Control and Collision Avoidance—0
Imitation Learning via Focused Satisficing—0
Structured Agent Distillation for Large Language Model—0
KinTwin: Imitation Learning with Torque and Muscle Driven Biomechanical Models Enables Precise Replication of Able-Bodied and Impaired Movement from Markerless Motion Capture—0
Zero-Shot Visual Generalization in Robot Manipulation—0
EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video—0
IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-TuningCode0
EnerVerse-AC: Envisioning Embodied Environments with Action Condition—0
Learning Long-Context Diffusion Policies via Past-Token Prediction—0
Imitation Learning for Adaptive Control of a Virtual Soft Exoglove—0
DataMIL: Selecting Data for Robot Imitation Learning with Datamodels—0
Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model—0
FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis—0
Distilling Realizable Students from Unrealizable Teachers—0
ChicGrasp: Imitation-Learning based Customized Dual-Jaw Gripper Control for Delicate, Irregular Bio-products Manipulation—0
Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation—0
What Matters for Batch Online Reinforcement Learning in Robotics?—0
Guiding Data Collection via Factored Scaling CurvesCode1
X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real—0
FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market Conditions—0
VIN-NBV: A View Introspection Network for Next-Best-View Selection for Resource-Efficient 3D Reconstruction—0
CubeDAgger: Improved Robustness of Interactive Imitation Learning without Violation of Dynamic Stability—0
CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations—0
D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation—0
Primal-dual algorithm for contextual stochastic combinatorial optimization—0
RIFT: Closed-Loop RL Fine-Tuning for Realistic and Controllable Traffic Simulation—0
Ergodic Generative Flows—0
AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control—0
The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning—0
Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning—0
FalconWing: An Open-Source Platform for Ultra-Light Fixed-Wing Aircraft Research—0
PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations—0
Imitation Learning for Autonomous Driving: Insights from Real-World TestingCode0
Generalization Capability for Imitation Learning—0
Offline Learning of Controllable Diverse Behaviors—0
CaRL: Learning Scalable Planning Policies with Simple RewardsCode2
Show:102550
← PrevPage 2 of 43Next →

No leaderboard results yet.