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 1571–1580 of 2122 papers

TitleStatusHype
ADAIL: Adaptive Adversarial Imitation Learning—0
Online Adaptive Learning for Runtime Resource Management of Heterogeneous SoCs—0
Adversarial Imitation Learning via Random Search—0
Imitation Learning with Sinkhorn DistancesCode1
Forward and inverse reinforcement learning sharing network weights and hyperparameters—0
Imitating Unknown Policies via ExplorationCode1
Visual Imitation Made Easy—0
Imitation Learning for Autonomous Trajectory Learning of Robot Arms in Space—0
Non-Adversarial Imitation Learning and its Connections to Adversarial MethodsCode0
Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning—0
Show:102550
← PrevPage 158 of 213Next →

No leaderboard results yet.