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.
End-to-End Imitation Learning for Optimal Asteroid Proximity Operations
Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
Coarse-to-Fine 3D Keyframe Transporter
VILP: Imitation Learning with Latent Video Planning
EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World
DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems
Diffusion-Based Planning for Autonomous Driving with Flexible Guidance
You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations
SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation
Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation
Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Tasks
Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning
Diffusion-Based Imitation Learning for Social Pose Generation
FDPP: Fine-tune Diffusion Policy with Human Preference
Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning
Generalizable Graph Neural Networks for Robust Power Grid Topology Control
Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data
Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination
Imitation Learning of MPC with Neural Networks: Error Guarantees and Sparsification
SR-Reward: Taking The Path More Traveled
Human-like Bots for Tactical Shooters Using Compute-Efficient Sensors
The intrinsic motivation of reinforcement and imitation learning for sequential tasks
Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker
Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking
SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch
Decoding fairness: a reinforcement learning perspective
Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
AdaCred: Adaptive Causal Decision Transformers with Feature Crediting
Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
Auto-bidding in real-time auctions via Oracle Imitation Learning (OIL)
Student-Informed Teacher Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.