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 551–600 of 2122 papers

TitleStatusHype
Grounding Language Plans in Demonstrations Through Counterfactual Perturbations—0
Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination—0
Interpretable Modeling of Deep Reinforcement Learning Driven Scheduling—0
IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History—0
Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but ImprovementCode1
Automated Feature Selection for Inverse Reinforcement Learning—0
Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium ProofCode0
Augmented Reality Demonstrations for Scalable Robot Imitation Learning—0
Information-Theoretic Distillation for Reference-less Summarization—0
What AIs are not Learning (and Why)—0
Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types—0
Offline Imitation of Badminton Player Behavior via Experiential Contexts and Brownian Motion—0
AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents—0
Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight—0
VITaL Pretraining: Visuo-Tactile Pretraining for Tactile and Non-Tactile Manipulation Policies—0
Supervised Fine-Tuning as Inverse Reinforcement Learning—0
SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy—0
DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation—0
TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation—0
Physics-informed Neural Motion Planning on Constraint Manifolds—0
Efficient Data Collection for Robotic Manipulation via Compositional Generalization—0
Globally Stable Neural Imitation PoliciesCode1
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D RepresentationsCode5
Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation—0
Behavior Generation with Latent ActionsCode3
RT-H: Action Hierarchies Using Language—0
Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)—0
Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking—0
PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning—0
Robust Policy Learning via Offline Skill Diffusion—0
DIGIC: Domain Generalizable Imitation Learning by Causal Discovery—0
Learning with Language-Guided State Abstractions—0
Imitation-regularized Optimal Transport on Networks: Provable Robustness and Application to Logistics Planning—0
ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games—0
Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning—0
Rethinking Mutual Information for Language Conditioned Skill Discovery on Imitation Learning—0
Expressive Whole-Body Control for Humanoid Robots—0
Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition—0
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory—0
Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy DiffusionCode1
HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent PathfindingCode1
Path Planning based on 2D Object Bounding-box—0
BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplay—0
CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation—0
Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future DirectionsCode2
DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models—0
Align Your Intents: Offline Imitation Learning via Optimal Transport—0
Tiny Reinforcement Learning for Quadruped Locomotion using Decision TransformersCode0
SPRINQL: Sub-optimal Demonstrations driven Offline Imitation LearningCode0
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in ControlCode1
Show:102550
← PrevPage 12 of 43Next →

No leaderboard results yet.