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.
The Pitfalls of Imitation Learning when Actions are Continuous
SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey
V-Max: A Reinforcement Learning Framework for Autonomous Driving
TLA: Tactile-Language-Action Model for Contact-Rich Manipulation
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies
Imitation Learning of Correlated Policies in Stackelberg Games
One-Shot Dual-Arm Imitation Learning
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning
PointVLA: Injecting the 3D World into Vision-Language-Action Models
A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing
EPR-GAIL: An EPR-Enhanced Hierarchical Imitation Learning Framework to Simulate Complex User Consumption Behaviors
Learning to Drive by Imitating Surrounding Vehicles
On a Connection Between Imitation Learning and RLHF
Look Before You Leap: Using Serialized State Machine for Language Conditioned Robotic Manipulation
Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interaction
dARt Vinci: Egocentric Data Collection for Surgical Robot Learning at Scale
Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning
Data-Efficient Learning from Human Interventions for Mobile Robots
Curating Demonstrations using Online Experience
Enhancing Autonomous Driving Safety with Collision Scenario Integration
Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation
A2Perf: Real-World Autonomous Agents Benchmark
FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interaction
POPGym Arcade: Parallel Pixelated POMDPs
Improving Retrospective Language Agents via Joint Policy Gradient Optimization
CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Driving
Perceptual Motor Learning with Active Inference Framework for Robust Lateral Control
CARIL: Confidence-Aware Regression in Imitation Learning for Autonomous Driving
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
ProDapt: Proprioceptive Adaptation using Long-term Memory Diffusion
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
RIZE: Regularized Imitation Learning via Distributional Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.