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 1026–1050 of 2122 papers

TitleStatusHype
Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars—0
AGIL: Learning Attention from Human for Visuomotor Tasks—0
Goal-Driven Imitation Learning from Observation by Inferring Goal Proximity—0
Goal-Directed Design Agents: Integrating Visual Imitation with One-Step Lookahead Optimization for Generative Design—0
Cross-Domain Imitation Learning with a Dual Structure—0
Goal-Conditioned Video Prediction—0
Autonomous Navigation in Complex Environments—0
Goal-conditioned Imitation Learning—0
Cross Domain Imitation Learning—0
Automating Deformable Gasket Assembly—0
A Geometric Perspective on Visual Imitation Learning—0
AdaCred: Adaptive Causal Decision Transformers with Feature Crediting—0
Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods—0
Global overview of Imitation Learning—0
Cross-domain Imitation from Observations—0
GHIL-Glue: Hierarchical Control with Filtered Subgoal Images—0
Get Back Here: Robust Imitation by Return-to-Distribution Planning—0
Gesture2Path: Imitation Learning for Gesture-aware Navigation—0
GenOSIL: Generalized Optimal and Safe Robot Control using Parameter-Conditioned Imitation Learning—0
CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning—0
AgentMixer: Multi-Agent Correlated Policy Factorization—0
GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation—0
GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and Imitation—0
Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning—0
Genetic Imitation Learning by Reward Extrapolation—0
Show:102550
← PrevPage 42 of 85Next →

No leaderboard results yet.