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 1626–1650 of 2122 papers

TitleStatusHype
Cross-Domain Imitation Learning with a Dual Structure—0
NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spaces—0
Imitative Non-Autoregressive Modeling for Trajectory Forecasting and Imputation—0
Predictive Modeling of Periodic Behavior for Human-Robot Symbiotic Walking—0
Active Imitation Learning with Noisy GuidanceCode1
Automatic Discovery of Interpretable Planning StrategiesCode0
Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets—0
A Simple Imitation Learning Method via Contrastive Regularization—0
Data Driven Aircraft Trajectory Prediction with Deep Imitation Learning—0
Language Conditioned Imitation Learning over Unstructured Data—0
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby StepsCode1
Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments with Multimodal Sensor Fusion—0
Improving Adversarial Text Generation by Modeling the Distant Future—0
Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation—0
Off-Policy Adversarial Inverse Reinforcement LearningCode1
An Imitation Game for Learning Semantic Parsers from User InteractionCode1
Disagreement-Regularized Imitation LearningCode1
Synthesizing Programmatic Policies that Inductively Generalize—0
Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards—0
Towards Embodied Scene Description—0
Informed Sampling for Diversity in Concept-to-Text NLG—0
Augmented Behavioral Cloning from ObservationCode1
VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban EnvironmentsCode1
GymFG: A Framework with a Gym Interface for FlightGear—0
Learning Constrained Adaptive Differentiable Predictive Control Policies With GuaranteesCode1
Show:102550
← PrevPage 66 of 85Next →

No leaderboard results yet.