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 1476–1500 of 2122 papers

TitleStatusHype
Behavioral Cloning from Noisy Demonstrations—0
Robust Imitation via Decision-Time Planning—0
Learning to Make Decisions via Submodular Regularization—0
Combining Imitation and Reinforcement Learning with Free Energy Principle—0
PERIL: Probabilistic Embeddings for hybrid Meta-Reinforcement and Imitation Learning—0
Robust Asymmetric Learning in POMDPsCode0
Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning—0
Imitation Learning for High Precision Peg-in-Hole Tasks—0
Multi-Instance Aware Localization for End-to-End Imitation Learning—0
Stochastic Action Prediction for Imitation Learning—0
Translating Natural Language Instructions to Computer Programs for Robot Manipulation—0
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II—0
Augmenting Policy Learning with Routines Discovered from a Single DemonstrationCode1
Rethink AI-based Power Grid Control: Diving Into Algorithm Design—0
Self-Imitation Advantage Learning—0
myGym: Modular Toolkit for Visuomotor Robotic Tasks—0
Learning Cross-Domain Correspondence for Control with Dynamics Cycle-ConsistencyCode1
Imitation Learning with Stability and Safety GuaranteesCode1
Learn to Play Tetris with Deep Reinforcement Learning—0
Using Enhanced Gaussian Cross-Entropy in Imitation Learning to Digging the First Diamond in Minecraft—0
Active Hierarchical Imitation and Reinforcement Learning—0
Human-in-the-Loop Imitation Learning using Remote Teleoperation—0
Learning Multi-Arm Manipulation Through Collaborative Teleoperation—0
Imitation-Based Active Camera Control with Deep Convolutional Neural Network—0
Flatland-RL : Multi-Agent Reinforcement Learning on Trains—0
Show:102550
← PrevPage 60 of 85Next →

No leaderboard results yet.