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 251–300 of 2122 papers

TitleStatusHype
Learning Cross-Domain Correspondence for Control with Dynamics Cycle-ConsistencyCode1
A Divergence Minimization Perspective on Imitation Learning MethodsCode1
Sparse Graphical Memory for Robust PlanningCode1
SQIL: Imitation Learning via Reinforcement Learning with Sparse RewardsCode1
Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from DemonstrationsCode1
Learning Exploration Policies for NavigationCode1
Learning Object Relation Graph and Tentative Policy for Visual NavigationCode1
Critic Guided Segmentation of Rewarding Objects in First-Person ViewsCode1
CRIL: Continual Robot Imitation Learning via Generative and Prediction ModelCode1
Latent Plans for Task-Agnostic Offline Reinforcement LearningCode1
Deep Imitation Learning for Bimanual Robotic ManipulationCode1
Counter-Strike Deathmatch with Large-Scale Behavioural CloningCode1
Language-Conditioned Imitation Learning for Robot Manipulation TasksCode1
Learning a Large Neighborhood Search Algorithm for Mixed Integer ProgramsCode1
Learning Selective Communication for Multi-Agent Path FindingCode1
JUICER: Data-Efficient Imitation Learning for Robotic AssemblyCode1
Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMsCode1
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesCode1
Learning Constrained Adaptive Differentiable Predictive Control Policies With GuaranteesCode1
KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics GradientsCode1
Invariant Causal Imitation Learning for Generalizable PoliciesCode1
Confidence-Aware Imitation Learning from Demonstrations with Varying OptimalityCode1
A Coupled Flow Approach to Imitation LearningCode1
Cross-Domain Imitation Learning via Optimal TransportCode1
Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection LearningCode1
Causal Imitation Learning under Temporally Correlated NoiseCode1
Inverse Reinforcement Learning without Reinforcement LearningCode1
Causal Imitative Model for Autonomous DrivingCode1
Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised LearningCode1
CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation TasksCode1
Curricular Subgoals for Inverse Reinforcement LearningCode1
Curriculum Offline Imitation LearningCode1
Intrinsic Reward Driven Imitation Learning via Generative ModelCode1
Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation LearningCode1
DeeCap: Dynamic Early Exiting for Efficient Image CaptioningCode1
IQ-Learn: Inverse soft-Q Learning for ImitationCode1
CDT: Cascading Decision Trees for Explainable Reinforcement LearningCode1
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online LearningCode1
LaND: Learning to Navigate from DisengagementsCode1
Discriminator-Weighted Offline Imitation Learning from Suboptimal DemonstrationsCode1
DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous DrivingCode1
DEMO: Reframing Dialogue Interaction with Fine-grained Element ModelingCode1
DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action AlignmentCode1
Chain-of-Thought Predictive ControlCode1
Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in MinecraftCode1
DERAIL: Diagnostic Environments for Reward And Imitation LearningCode1
DexMV: Imitation Learning for Dexterous Manipulation from Human VideosCode1
Leveraging Locality to Boost Sample Efficiency in Robotic ManipulationCode1
Learning to combine primitive skills: A step towards versatile robotic manipulationCode1
Imitation Learning with Sinkhorn DistancesCode1
Show:102550
← PrevPage 6 of 43Next →

No leaderboard results yet.