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 2001–2050 of 2122 papers

TitleStatusHype
Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image TranslationCode0
Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation LearningCode1
Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning—0
Fast Policy Learning through Imitation and Reinforcement—0
Learning Self-Imitating Diverse Policies—0
Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement LearningCode0
Inverse Rational Control: Inferring What You Think from How You Forage—0
Verifiable Reinforcement Learning via Policy ExtractionCode1
Multi-task Maximum Entropy Inverse Reinforcement LearningCode0
Maximum Causal Tsallis Entropy Imitation Learning—0
Imitating Latent Policies from ObservationCode1
End-to-end driving simulation via angle branched network—0
Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning—0
Behavioral Cloning from ObservationCode1
Zero-Shot Visual ImitationCode0
Event Extraction with Generative Adversarial Imitation Learning—0
Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills—0
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue SystemsCode0
Learning Contracting Vector Fields For Stable Imitation Learning—0
Hindsight is Only 50/50: Unsuitability of MDP based Approximate POMDP Solvers for Multi-resolution Information Gathering—0
Learning to Search via Retrospective Imitation—0
Universal Planning NetworksCode0
Visual Robot Task PlanningCode0
Safe end-to-end imitation learning for model predictive control—0
Generating Multi-Agent Trajectories using Programmatic Weak SupervisionCode0
Imitation Learning with Concurrent Actions in 3D Games—0
OIL: Observational Imitation Learning—0
Multi-Agent Imitation Learning for Driving SimulationCode0
Hierarchical Imitation and Reinforcement Learning—0
Reinforcement and Imitation Learning for Diverse Visuomotor SkillsCode0
Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process—0
Convergence of Value Aggregation for Imitation Learning—0
Global overview of Imitation Learning—0
Faster Reinforcement Learning with Expert State Sequences—0
Model-based imitation learning from state trajectories—0
Imitation Learning from Visual Data with Multiple Intentions—0
Learning Robust Rewards with Adverserial Inverse Reinforcement Learning—0
Deterministic Policy Imitation Gradient Algorithm—0
Parametrized Hierarchical Procedures for Neural Programming—0
CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven CommunicationCode0
AI2-THOR: An Interactive 3D Environment for Visual AICode1
Multimodal Storytelling via Generative Adversarial Imitation Learning—0
State Aware Imitation Learning—0
Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces—0
CARLA: An Open Urban Driving SimulatorCode0
Policy Optimization by Genetic Distillation—0
Burn-In Demonstrations for Multi-Modal Imitation Learning—0
Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality TeleoperationCode0
Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation LearningCode0
End-to-end Driving via Conditional Imitation LearningCode0
Show:102550
← PrevPage 41 of 43Next →

No leaderboard results yet.