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 501–525 of 2122 papers

TitleStatusHype
Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks—0
DITTO: Offline Imitation Learning with World Models—0
Data Quality in Imitation Learning—0
Diverse Imitation Learning via Self-Organizing Generative Models—0
Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble—0
Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning—0
Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations—0
Bridging the Resource Gap: Deploying Advanced Imitation Learning Models onto Affordable Embedded Platforms—0
DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning—0
DataMIL: Selecting Data for Robot Imitation Learning with Datamodels—0
Data-Efficient Learning from Human Interventions for Mobile Robots—0
Back to Reality for Imitation Learning—0
Data-driven Traffic Simulation: A Comprehensive Review—0
Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning—0
Aligning Robot and Human Representations—0
End-to-End Differentiable Adversarial Imitation Learning—0
Data Driven Aircraft Trajectory Prediction with Deep Imitation Learning—0
Data augmentation for efficient learning from parametric experts—0
dARt Vinci: Egocentric Data Collection for Surgical Robot Learning at Scale—0
Aligning Agents like Large Language Models—0
CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation—0
Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning—0
Cut-and-Approximate: 3D Shape Reconstruction from Planar Cross-sections with Deep Reinforcement Learning—0
Avoidance Learning Using Observational Reinforcement Learning—0
Alibaba’s Submission for the WMT 2020 APE Shared Task: Improving Automatic Post-Editing with Pre-trained Conditional Cross-Lingual BERT—0
Show:102550
← PrevPage 21 of 85Next →

No leaderboard results yet.