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 1021–1030 of 2122 papers

TitleStatusHype
ENTL: Embodied Navigation Trajectory Learner—0
Lagrangian Generative Adversarial Imitation Learning with Safety—0
CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving—0
Entity-Centric Coreference Resolution with Model Stacking—0
EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning—0
CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving—0
Adversarial Imitation Learning from Video using a State Observer—0
ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation—0
Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning—0
Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks—0
Show:102550
← PrevPage 103 of 213Next →

No leaderboard results yet.