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 901–950 of 2122 papers

TitleStatusHype
Interactive Text Generation—0
Teach a Robot to FISH: Versatile Imitation from One Minute of DemonstrationsCode1
MEGA-DAgger: Imitation Learning with Multiple Imperfect ExpertsCode0
LS-IQ: Implicit Reward Regularization for Inverse Reinforcement LearningCode1
Automated Task-Time Interventions to Improve Teamwork using Imitation Learning—0
Learning Large Neighborhood Search for Vehicle Routing in Airport Ground HandlingCode1
Diffusion Model-Augmented Behavioral Cloning—0
Simulation of robot swarms for learning communication-aware coordinationCode0
Language-Driven Representation Learning for RoboticsCode2
K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs—0
Dual RL: Unification and New Methods for Reinforcement and Imitation LearningCode1
Pretraining Language Models with Human PreferencesCode1
When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement LearningCode1
Unlabeled Imperfect Demonstrations in Adversarial Imitation LearningCode1
CILP: Co-simulation based Imitation Learner for Dynamic Resource Provisioning in Cloud Computing EnvironmentsCode0
Learning to Simulate Daily Activities via Modeling Dynamic Human NeedsCode1
Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical StudyCode0
Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban EnvironmentsCode1
ManiSkill2: A Unified Benchmark for Generalizable Manipulation SkillsCode1
Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation—0
Scaling Vision-based End-to-End Driving with Multi-View Attention Learning—0
Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction VideosCode0
DITTO: Offline Imitation Learning with World Models—0
A Strong Baseline for Batch Imitation Learning—0
Target-based Surrogates for Stochastic OptimizationCode0
Aligning Robot and Human Representations—0
Synthesizing Physical Character-Scene Interactions—0
Visual Imitation Learning with Patch RewardsCode1
Superhuman FairnessCode0
PADL: Language-Directed Physics-Based Character ControlCode1
Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation PoliciesCode0
Hierarchical Imitation Learning with Vector Quantized ModelsCode0
Optimal Decision Tree Policies for Markov Decision ProcessesCode0
Improving Behavioural Cloning with Positive Unlabeled Learning—0
Theoretical Analysis of Offline Imitation With Supplementary DatasetCode0
Language-guided Task Adaptation for Imitation Learning—0
SMART: Self-supervised Multi-task pretrAining with contRol Transformers—0
Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense—0
Domain-adapted Learning and Imitation: DRL for Power Arbitrage—0
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis—0
DIRECT: Learning from Sparse and Shifting Rewards using Discriminative Reward Co-Training—0
PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNavCode1
Adaptive Neural Networks Using Residual Fitting—0
Orbit: A Unified Simulation Framework for Interactive Robot Learning EnvironmentsCode5
Genetic Imitation Learning by Reward Extrapolation—0
Explaining Imitation Learning through Frames—0
Imitation Learning As State Matching via Differentiable Physics—0
RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension—0
Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary TasksCode1
Bayesian Learning for Dynamic Inference—0
Show:102550
← PrevPage 19 of 43Next →

No leaderboard results yet.