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 1741–1750 of 2122 papers

TitleStatusHype
MANGA: Method Agnostic Neural-policy Generalization and Adaptation—0
On Value Discrepancy of Imitation Learning—0
Motion Reasoning for Goal-Based Imitation Learning—0
Accelerating Training in Pommerman with Imitation and Reinforcement Learning—0
A Divergence Minimization Perspective on Imitation Learning MethodsCode1
Learning One-Shot Imitation from Humans without HumansCode0
Learning from Trajectories via Subgoal DiscoveryCode0
DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning—0
Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning—0
Positive-Unlabeled Reward Learning—0
Show:102550
← PrevPage 175 of 213Next →

No leaderboard results yet.