SOTAVerified

Imitation Learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 526–550 of 2122 papers

TitleStatusHype
Curriculum Offline Imitating Learning—0
Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series—0
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents—0
Accelerating Inverse Reinforcement Learning with Expert Bootstrapping—0
Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation—0
Curating Demonstrations using Online Experience—0
A Graph-based Adversarial Imitation Learning Framework for Reliable & Realtime Fleet Scheduling in Urban Air Mobility—0
CubeDAgger: Improved Robustness of Interactive Imitation Learning without Violation of Dynamic Stability—0
CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games—0
AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning—0
AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent—0
Perceptual Motor Learning with Active Inference Framework for Robust Lateral Control—0
Entity-Centric Coreference Resolution with Model Stacking—0
Ergodic Generative Flows—0
Evolutionary Selective Imitation: Interpretable Agents by Imitation Learning Without a Demonstrator—0
Expressive Whole-Body Control for Humanoid Robots—0
Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration—0
Cross-Episodic Curriculum for Transformer Agents—0
Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars—0
AGIL: Learning Attention from Human for Visuomotor Tasks—0
Enhanced DACER Algorithm with High Diffusion Efficiency—0
Cross-Domain Imitation Learning with a Dual Structure—0
Autonomous Navigation in Complex Environments—0
Cross Domain Imitation Learning—0
Automating Deformable Gasket Assembly—0
Show:102550
← PrevPage 22 of 85Next →

No leaderboard results yet.