Imitation Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration
Adapting a World Model for Trajectory Following in a 3D Game
Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models
Improving In-Context Learning with Reasoning Distillation
Toward Aligning Human and Robot Actions via Multi-Modal Demonstration Learning
Diffusion Models for Robotic Manipulation: A Survey
CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Driving
AssistanceZero: Scalably Solving Assistance Games
Stratified Expert Cloning with Adaptive Selection for User Retention in Large-Scale Recommender Systems
Tool-as-Interface: Learning Robot Policies from Human Tool Usage through Imitation Learning
Dexterous Manipulation through Imitation Learning: A Survey
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers
Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error
ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos
HACTS: a Human-As-Copilot Teleoperation System for Robot Learning
CBIL: Collective Behavior Imitation Learning for Fish from Real Videos
Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models
Robust Offline Imitation Learning Through State-level Trajectory Stitching
Empirical Analysis of Sim-and-Real Cotraining Of Diffusion Policies For Planar Pushing from Pixels
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation
Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Bridging the Sim-to-real Gap: A Control Framework for Imitation Learning of Model Predictive Control
Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation
Bootstrapped Model Predictive Control
BEAC: Imitating Complex Exploration and Task-oriented Behaviors for Invisible Object Nonprehensile Manipulation
TamedPUMA: safe and stable imitation learning with geometric fabrics
End-to-end Sketch-Guided Path Planning through Imitation Learning for Autonomous Mobile Robots
Learning 3D Scene Analogies with Neural Contextual Scene Maps
Denoising-based Contractive Imitation Learning
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints
HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.