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 1976–2000 of 2122 papers

TitleStatusHype
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation LearningCode0
Sample-Efficient Imitation Learning via Generative Adversarial NetsCode0
3D Ego-Pose Estimation via Imitation Learning—0
Imitation Learning for Neural Morphological String TransductionCode0
Shared Multi-Task Imitation Learning for Indoor Self-Navigation—0
Risk-Sensitive Generative Adversarial Imitation Learning—0
Multi-Agent Generative Adversarial Imitation LearningCode1
EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning—0
Generative Adversarial Imitation from ObservationCode0
Bipedal Walking Robot using Deep Deterministic Policy GradientCode0
Extracting Contact and Motion from Manipulation Videos—0
CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving—0
Universal Planning Networks: Learning Generalizable Representations for Visuomotor ControlCode0
Learning How to Actively Learn: A Deep Imitation Learning ApproachCode0
End-to-End Deep Imitation Learning: Robot Soccer Case Study—0
The Virtuous Machine - Old Ethics for New Technology?—0
Adversarial Active Exploration for Inverse Dynamics Model Learning—0
Learning Existing Social Conventions via Observationally Augmented Self-Play—0
Learning Neural Parsers with Deterministic Differentiable Imitation Learning—0
Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations—0
Conditional Affordance Learning for Driving in Urban EnvironmentsCode0
Learning Policy Representations in Multiagent Systems—0
Self-Imitation LearningCode0
Accelerating Imitation Learning with Predictive Models—0
AGIL: Learning Attention from Human for Visuomotor Tasks—0
Show:102550
← PrevPage 80 of 85Next →

No leaderboard results yet.