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.
MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations
Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space
Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy
What Do You Need for Diverse Trajectory Stitching in Diffusion Planning?
ProgRM: Build Better GUI Agents with Progress Rewards
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only
Guided Policy Optimization under Partial Observability
FLARE: Robot Learning with Implicit World Modeling
UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning
Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones
Structured Agent Distillation for Large Language Model
Imitation Learning via Focused Satisficing
KinTwin: Imitation Learning with Torque and Muscle Driven Biomechanical Models Enables Precise Replication of Able-Bodied and Impaired Movement from Markerless Motion Capture
EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
Zero-Shot Visual Generalization in Robot Manipulation
IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning
Imitation Learning for Adaptive Control of a Virtual Soft Exoglove
FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis
Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model
Distilling Realizable Students from Unrealizable Teachers
Learning Long-Context Diffusion Policies via Past-Token Prediction
DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
EnerVerse-AC: Envisioning Embodied Environments with Action Condition
Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation
ChicGrasp: Imitation-Learning based Customized Dual-Jaw Gripper Control for Delicate, Irregular Bio-products Manipulation
Guiding Data Collection via Factored Scaling Curves
What Matters for Batch Online Reinforcement Learning in Robotics?
X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market Conditions
VIN-NBV: A View Introspection Network for Next-Best-View Selection for Resource-Efficient 3D Reconstruction
D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation
CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning
RIFT: Closed-Loop RL Fine-Tuning for Realistic and Controllable Traffic Simulation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.