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 1001–1050 of 2122 papers

TitleStatusHype
Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving—0
Planning for Sample Efficient Imitation LearningCode1
Inferring Versatile Behavior from Demonstrations by Matching Geometric DescriptorsCode0
Model Predictive Control via On-Policy Imitation Learning—0
Robust Imitation of a Few Demonstrations with a Backwards Model—0
Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding—0
Model-Based Imitation Learning for Urban DrivingCode2
Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point CloudsCode1
Eliciting Compatible Demonstrations for Multi-Human Imitation Learning—0
Iterative Document-level Information Extraction via Imitation LearningCode0
Real World Offline Reinforcement Learning with Realistic Data Source—0
Travel the Same Path: A Novel TSP Solving StrategyCode0
Markup-to-Image Diffusion Models with Scheduled SamplingCode1
Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues—0
Don't Copy the Teacher: Data and Model Challenges in Embodied DialogueCode0
A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning—0
VIMA: General Robot Manipulation with Multimodal PromptsCode2
Option-Aware Adversarial Inverse Reinforcement Learning for Robotic ControlCode1
CW-ERM: Improving Autonomous Driving Planning with Closed-loop Weighted Empirical Risk MinimizationCode2
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees—0
Learning Perception-Aware Agile Flight in Cluttered Environments—0
Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field—0
Extraneousness-Aware Imitation Learning—0
Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees—0
Dissipative Imitation Learning for Robust Dynamic Output Feedback—0
Regularized Soft Actor-Critic for Behavior Transfer Learning—0
Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective—0
On Efficient Online Imitation Learning via Classification—0
Unsupervised Reward Shaping for a Robotic Sequential Picking Task from Visual Observations in a Logistics ScenarioCode0
Learn what matters: cross-domain imitation learning with task-relevant embeddings—0
Graph Neural Networks for Multi-Robot Active Information Acquisition—0
Proximal Point Imitation LearningCode1
Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation—0
Optimizing Crop Management with Reinforcement Learning and Imitation Learning—0
Gesture2Path: Imitation Learning for Gesture-aware Navigation—0
MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation—0
Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic EnvironmentsCode1
Latent Plans for Task-Agnostic Offline Reinforcement LearningCode1
Spatial-Temporal Deep Embedding for Vehicle Trajectory Reconstruction from High-Angle Video—0
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose EstimatorsCode0
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions—0
Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations—0
CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation—0
Signs of Language: Embodied Sign Language Fingerspelling Acquisition from Demonstrations for Human-Robot Interaction—0
Task-Agnostic Learning to Accomplish New Tasks—0
Levenshtein OCRCode0
TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification—0
Co-Imitation: Learning Design and Behaviour by Imitation—0
MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization—0
Weighted Maximum Entropy Inverse Reinforcement Learning—0
Show:102550
← PrevPage 21 of 43Next →

No leaderboard results yet.