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 1876–1900 of 2122 papers

TitleStatusHype
Randomized Adversarial Imitation Learning for Autonomous Driving—0
Uncertainty-Aware Data Aggregation for Deep Imitation Learning—0
Reinforced Imitation Learning from Observations—0
Sample Efficient Imitation Learning for Continuous Control—0
Modeling the Long Term Future in Model-Based Reinforcement Learning—0
Visual Imitation with a Minimal Adversary—0
Trajectory VAE for multi-modal imitation—0
Learning to Drive by Observing the Best and Synthesizing the Worst—0
Adversarial Exploration Strategy for Self-Supervised Imitation Learning—0
SIMILE: Introducing Sequential Information towards More Effective Imitation Learning—0
Learning from Noisy Demonstration Sets via Meta-Learned Suitability Assessor—0
Exploring the Limitations of Behavior Cloning for Autonomous DrivingCode0
Efficient Motion Planning for Automated Lane Change based on Imitation Learning and Mixed-Integer OptimizationCode0
Gaze Training by Modulated Dropout Improves Imitation Learning—0
Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation—0
Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning—0
A Comparison of Policy Search in Joint Space and Cartesian Space for Refinement of Skills—0
Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from ObservationsCode0
Few-Shot Bayesian Imitation Learning with Logical Program Policies—0
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight—0
Reinforced Imitation in Heterogeneous Action Space—0
Generative predecessor models for sample-efficient imitation learning—0
Guided Meta-Policy Search—0
Cortical Mirror-System Activation During Real-Life Game Playing: An Intracranial Electroencephalography (EEG) Study—0
Hindsight Generative Adversarial Imitation Learning—0
Show:102550
← PrevPage 76 of 85Next →

No leaderboard results yet.