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 1071–1080 of 2122 papers

TitleStatusHype
Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control—0
Quantum Imitation Learning—0
RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning—0
RaCIL: Ray Tracing based Multi-UAV Obstacle Avoidance through Composite Imitation Learning—0
RadGrad: Active learning with loss gradients—0
RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning—0
RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning—0
Randomized Adversarial Imitation Learning for Autonomous Driving—0
Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning—0
Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)—0
Show:102550
← PrevPage 108 of 213Next →

No leaderboard results yet.