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 1551–1600 of 2122 papers

TitleStatusHype
Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking—0
Mimicking the Maestro: Exploring the Efficacy of a Virtual AI Teacher in Fine Motor Skill Acquisition—0
Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Competitive Games—0
MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation—0
MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations—0
Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models—0
Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)—0
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation—0
Model-based Adversarial Imitation Learning—0
Model-based imitation learning from state trajectories—0
Model-Based Imitation Learning Using Entropy Regularization of Model and Policy—0
Model-based Offline Imitation Learning with Non-expert Data—0
Model-Based Reinforcement Learning via Stochastic Hybrid Models—0
Model-Based Runtime Monitoring with Interactive Imitation Learning—0
Model-based trajectory stitching for improved behavioural cloning and its applications—0
Model-Free Imitation Learning with Policy Optimization—0
Modeling Human Driving Behavior through Generative Adversarial Imitation Learning—0
Modeling Strong and Human-Like Gameplay with KL-Regularized Search—0
Modeling the Long Term Future in Model-Based Reinforcement Learning—0
Modelling Agent Policies with Interpretable Imitation Learning—0
Model Predictive Control via On-Policy Imitation Learning—0
ModSkill: Physical Character Skill Modularization—0
MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees—0
MOMA-Force: Visual-Force Imitation for Real-World Mobile Manipulation—0
MOT: A Mixture of Actors Reinforcement Learning Method by Optimal Transport for Algorithmic Trading—0
Motion Generation Using Bilateral Control-Based Imitation Learning with Autoregressive Learning—0
Motion Reasoning for Goal-Based Imitation Learning—0
Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning—0
Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects—0
MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation—0
Multi-Action Dialog Policy Learning with Interactive Human Teaching—0
Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance—0
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard—0
Multi-Agent Imitation Learning with Copulas—0
Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques—0
Emergent Social Learning via Multi-agent Reinforcement Learning—0
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning—0
Multi-Instance Aware Localization for End-to-End Imitation Learning—0
Multimodal End-to-End Autonomous Driving—0
Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets—0
Multimodal Storytelling via Generative Adversarial Imitation Learning—0
Multi-Object Navigation in real environments using hybrid policies—0
Multi-Stage Cable Routing through Hierarchical Imitation Learning—0
Multi-Task Conditional Imitation Learning for Autonomous Navigation at Crowded Intersections—0
Multi-Task Imitation Learning for Linear Dynamical Systems—0
Multi-task Learning with Attention for End-to-end Autonomous Driving—0
Multi-Task Policy Search—0
Multi-task real-robot data with gaze attention for dual-arm fine manipulation—0
Naturalistic Robot Arm Trajectory Generation via Representation Learning—0
Navigation by Imitation in a Pedestrian-Rich Environment—0
Show:102550
← PrevPage 32 of 43Next →

No leaderboard results yet.