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 601–610 of 2122 papers

TitleStatusHype
A Training-Free Framework for Precise Mobile Manipulation of Small Everyday Objects—0
Active Learning within Constrained Environments through Imitation of an Expert Questioner—0
Fast Bilateral Teleoperation and Imitation Learning Using Sensorless Force Control via Accurate Dynamics Model—0
Faster Reinforcement Learning with Expert State Sequences—0
Conditional Vehicle Trajectories Prediction in CARLA Urban Environment—0
Conditional Kernel Imitation Learning for Continuous State Environments—0
Conditional Imitation Learning for Multi-Agent Games—0
Conditional Driving from Natural Language Instructions—0
Atari-GPT: Benchmarking Multimodal Large Language Models as Low-Level Policies in Atari Games—0
Concurrent Training Improves the Performance of Behavioral Cloning from Observation—0
Show:102550
← PrevPage 61 of 213Next →

No leaderboard results yet.