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 151–200 of 2122 papers

TitleStatusHype
When should we prefer Decision Transformers for Offline Reinforcement Learning?Code1
Multi-task Hierarchical Adversarial Inverse Reinforcement LearningCode1
A Coupled Flow Approach to Imitation LearningCode1
Learning to Extrapolate: A Transductive ApproachCode1
Self-Supervised Adversarial Imitation LearningCode1
Goal-Conditioned Imitation Learning using Score-based Diffusion PoliciesCode1
Chain-of-Thought Predictive ControlCode1
Improving Code Generation by Training with Natural Language FeedbackCode1
Training Language Models with Language Feedback at ScaleCode1
Inverse Reinforcement Learning without Reinforcement LearningCode1
Optimal Transport for Offline Imitation LearningCode1
How To Guide Your Learner: Imitation Learning with Active Adaptive Expert InvolvementCode1
Teach a Robot to FISH: Versatile Imitation from One Minute of DemonstrationsCode1
LS-IQ: Implicit Reward Regularization for Inverse Reinforcement LearningCode1
Learning Large Neighborhood Search for Vehicle Routing in Airport Ground HandlingCode1
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
Learning to Simulate Daily Activities via Modeling Dynamic Human NeedsCode1
Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban EnvironmentsCode1
ManiSkill2: A Unified Benchmark for Generalizable Manipulation SkillsCode1
Visual Imitation Learning with Patch RewardsCode1
PADL: Language-Directed Physics-Based Character ControlCode1
PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNavCode1
Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary TasksCode1
End-to-End Imitation Learning with Safety Guarantees using Control Barrier FunctionsCode1
CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation LearningCode1
A System for Morphology-Task Generalization via Unified Representation and Behavior DistillationCode1
Dynamic Conditional Imitation Learning for Autonomous DrivingCode1
DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous DrivingCode1
Planning for Sample Efficient Imitation LearningCode1
Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point CloudsCode1
Markup-to-Image Diffusion Models with Scheduled SamplingCode1
Option-Aware Adversarial Inverse Reinforcement Learning for Robotic ControlCode1
Proximal Point Imitation LearningCode1
Latent Plans for Task-Agnostic Offline Reinforcement LearningCode1
Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic EnvironmentsCode1
Learning Soccer Juggling Skills with Layer-wise Mixture-of-ExpertsCode1
Discriminator-Weighted Offline Imitation Learning from Suboptimal DemonstrationsCode1
Target-absent Human AttentionCode1
Robust Imitation Learning against Variations in Environment DynamicsCode1
A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewardsCode1
Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object ManipulationCode1
Imitation Learning via Differentiable PhysicsCode1
Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective TrajectoriesCode1
An Empirical Investigation of Representation Learning for ImitationCode1
KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics GradientsCode1
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human ModelsCode1
What Matters in Language Conditioned Robotic Imitation Learning over Unstructured DataCode1
Show:102550
← PrevPage 4 of 43Next →

No leaderboard results yet.