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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1826–1850 of 2122 papers

Title	Date	Tasks	Status	Hype
Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation	Jul 12, 2019	Decision MakingImitation Learning	—Unverified	0
Imitation-Projected Programmatic Reinforcement Learning	Jul 11, 2019	continuous-controlContinuous Control	—Unverified	0
Utilizing Eye Gaze to Enhance the Generalization of Imitation Networks to Unseen Environments	Jul 10, 2019	Autonomous DrivingImitation Learning	—Unverified	0
Hybrid system identification using switching density networks	Jul 9, 2019	Imitation Learningregression	CodeCode Available	0
Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations	Jul 9, 2019	Imitation Learningreinforcement-learning	CodeCode Available	0
On-Policy Robot Imitation Learning from a Converging Supervisor	Jul 8, 2019	continuous-controlContinuous Control	—Unverified	0
Learning a Behavioral Repertoire from Demonstrations	Jul 5, 2019	Imitation LearningReinforcement Learning	—Unverified	0
Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation	Jul 4, 2019	FormImitation Learning	—Unverified	0
Co-training for Policy Learning	Jul 3, 2019	Combinatorial Optimizationcontinuous-control	CodeCode Available	0
Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model	Jul 3, 2019	General KnowledgeImitation Learning	—Unverified	0
Active Learning within Constrained Environments through Imitation of an Expert Questioner	Jul 1, 2019	Active LearningImitation Learning	—Unverified	0
Sample Efficient Learning of Path Following and Obstacle Avoidance Behavior for Quadrotors	Jun 28, 2019	Collision AvoidanceImitation Learning	—Unverified	0
Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments	Jun 27, 2019	Imitation Learning	CodeCode Available	0
PyRep: Bringing V-REP to Deep Robot Learning	Jun 26, 2019	Imitation Learningreinforcement-learning	CodeCode Available	0
Learning to Interactively Learn and Assist	Jun 24, 2019	Imitation LearningQuestion Answering	—Unverified	0
Learning Belief Representations for Imitation Learning in POMDPs	Jun 22, 2019	continuous-controlContinuous Control	CodeCode Available	0
Wasserstein Adversarial Imitation Learning	Jun 19, 2019	Imitation Learningreinforcement-learning	—Unverified	0
RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstration	Jun 18, 2019	Imitation Learningreinforcement-learning	—Unverified	0
RadGrad: Active learning with loss gradients	Jun 18, 2019	Active LearningImitation Learning	—Unverified	0
Sample-efficient Adversarial Imitation Learning from Observation	Jun 18, 2019	Imitation LearningReinforcement Learning	—Unverified	0
MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning	Jun 16, 2019	Game of GoImitation Learning	CodeCode Available	1
Goal-conditioned Imitation Learning	Jun 13, 2019	Imitation LearningReinforcement Learning	CodeCode Available	0
Imitation Learning of Neural Spatio-Temporal Point Processes	Jun 13, 2019	Computational EfficiencyImitation Learning	CodeCode Available	0
Learning to Score Behaviors for Guided Policy Optimization	Jun 11, 2019	Efficient ExplorationImitation Learning	CodeCode Available	0
Multimodal End-to-End Autonomous Driving	Jun 7, 2019	Autonomous DrivingAutonomous Vehicles	—Unverified	0

Show:10 25 50

← PrevPage 74 of 85Next →

No leaderboard results yet.