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 1861–1870 of 2122 papers

TitleStatusHype
Exploring Computational User Models for Agent Policy SummarizationCode0
Imitation Learning as f-Divergence Minimization—0
Adversarial Imitation Learning from Incomplete DemonstrationsCode0
LeTS-Drive: Driving in a Crowd by Learning from Tree Search—0
Causal Confusion in Imitation LearningCode0
Efficient Kirszbraun Extension with Applications to Regression—0
SQIL: Imitation Learning via Reinforcement Learning with Sparse RewardsCode1
Provably Efficient Imitation Learning from Observation AloneCode0
Learning to Reason in Large Theories without Imitation—0
Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning—0
Show:102550
← PrevPage 187 of 213Next →

No leaderboard results yet.