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 1451–1460 of 2122 papers

TitleStatusHype
Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness—0
Learning Robust Rewards with Adverserial Inverse Reinforcement Learning—0
Learning Self-Imitating Diverse Policies—0
Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations—0
Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories—0
Learning Solution Manifolds for Control Problems via Energy Minimization—0
Learning Space-Time Semantic Correspondences—0
Learning Stable Koopman Embeddings for Identification and Control—0
Learning Strategy Representation for Imitation Learning in Multi-Agent Games—0
Learning Task-Agnostic Skill Bases to Uncover Motor Primitives in Animal Behaviors—0
Show:102550
← PrevPage 146 of 213Next →

No leaderboard results yet.