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.
Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence
SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
Human-Robot Navigation using Event-based Cameras and Reinforcement Learning
Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation
From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
Towards Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning
Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism
UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation
Solving the Job Shop Scheduling Problem with Graph Neural Networks: A Customizable Reinforcement Learning Environment
Reinforcement Learning via Implicit Imitation Guidance
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
SpikePingpong: High-Frequency Spike Vision-based Robot Learning for Precise Striking in Table Tennis Game
FlowOE: Imitation Learning with Flow Policy from Ensemble RL Experts for Optimal Execution under Heston Volatility and Concave Market Impacts
BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning
Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion
A Smooth Sea Never Made a Skilled $\texttt{SAILOR}$: Robust Imitation via Learning to Search
Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving
SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning
Rodrigues Network for Learning Robot Actions
Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks
WoMAP: World Models For Embodied Open-Vocabulary Object Localization
Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey
RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer
Enhanced DACER Algorithm with High Diffusion Efficiency
Streaming Flow Policy: Simplifying diffusion$/$flow-matching policies by treating action trajectories as flow trajectories
ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
Learning Compositional Behaviors from Demonstration and Language
SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning
Spatial RoboGrasp: Generalized Robotic Grasping Control Policy
Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning
Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^π$-Realizable MDPs
ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving
Online Knowledge Distillation with Reward Guidance
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.