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 1461–1470 of 2122 papers

TitleStatusHype
Learning Task Decomposition with Order-Memory Policy Network—0
Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning—0
Learning the optimal state-feedback via supervised imitation learning—0
Learning the Representation of Behavior Styles with Imitation Learning—0
Learning to Actively Learn Neural Machine Translation—0
Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy—0
Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning—0
Learning to Defend by Learning to Attack—0
Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning—0
Learning to Drive Anywhere—0
Show:102550
← PrevPage 147 of 213Next →

No leaderboard results yet.