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 1101–1125 of 2122 papers

TitleStatusHype
ARC -- Actor Residual Critic for Adversarial Imitation Learning—0
Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble—0
TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous DrivingCode3
Minimax Optimal Online Imitation Learning via Replay EstimationCode0
Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning—0
TaSIL: Taylor Series Imitation LearningCode0
Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective TrajectoriesCode1
Data augmentation for efficient learning from parametric experts—0
Chain of Thought Imitation with Procedure Cloning—0
Learning Energy Networks with Generalized Fenchel-Young Losses—0
IL-flOw: Imitation Learning from Observation using Normalizing Flows—0
Generalizing to New Tasks via One-Shot Compositional Subgoals—0
An Empirical Investigation of Representation Learning for ImitationCode1
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation—0
Delayed Reinforcement Learning by Imitation—0
Diverse Imitation Learning via Self-Organizing Generative Models—0
Hitting time for Markov decision process—0
SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning—0
What Makes A Good Fisherman? Linear Regression under Self-Selection Bias—0
Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations—0
ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated CharactersCode3
KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics GradientsCode1
Learning Value Functions from Undirected State-only Experience—0
From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation—0
Task-Induced Representation Learning—0
Show:102550
← PrevPage 45 of 85Next →

No leaderboard results yet.