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 626–650 of 2122 papers

TitleStatusHype
Steering Language Models with Game-Theoretic SolversCode9
Multi-Object Navigation in real environments using hybrid policies—0
Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations—0
Visual Imitation Learning with Calibrated Contrastive Representation—0
Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance—0
LangProp: A code optimization framework using Large Language Models applied to drivingCode2
Offline Imitation Learning by Controlling the Effective Planning Horizon—0
Imitation Learning Inputting Image Feature to Each Layer of Neural Network—0
Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation—0
AgentMixer: Multi-Agent Correlated Policy Factorization—0
Learning Stable Koopman Embeddings for Identification and Control—0
Robotic Imitation of Human Actions—0
Multi-task real-robot data with gaze attention for dual-arm fine manipulation—0
COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy—0
LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage ControlCode1
Robust Imitation Learning for Automated Game Testing—0
Behavioural Cloning in VizDoom—0
Autonomous Navigation in Complex Environments—0
Towards an Adaptable and Generalizable Optimization Engine in Decision and Control: A Meta Reinforcement Learning Approach—0
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation—0
SwapTransformer: highway overtaking tactical planner model via imitation learning on OSHA datasetCode1
GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation—0
GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitation—0
Agnostic Interactive Imitation Learning: New Theory and Practical AlgorithmsCode0
An Integrated Imitation and Reinforcement Learning Methodology for Robust Agile Aircraft Control with Limited Pilot Demonstration Data—0
Show:102550
← PrevPage 26 of 85Next →

No leaderboard results yet.