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 1276–1300 of 2122 papers

TitleStatusHype
Cross-Domain Imitation Learning via Optimal TransportCode1
Goal-Directed Design Agents: Integrating Visual Imitation with One-Step Lookahead Optimization for Generative Design—0
Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning—0
A Critique of Strictly Batch Imitation Learning—0
Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion ExtractionCode0
Fast fixed-backbone protein sequence and rotamer design—0
State-Only Imitation Learning by Trajectory Distribution Matching—0
Lagrangian Generative Adversarial Imitation Learning with Safety—0
Learning the Representation of Behavior Styles with Imitation Learning—0
Transferring Hierarchical Structure with Dual Meta Imitation Learning—0
Plan Your Target and Learn Your Skills: State-Only Imitation Learning via Decoupled Policy Optimization—0
Emergent Communication at ScaleCode1
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning—0
Auto-Encoding Inverse Reinforcement Learning—0
Lagrangian Method for Episodic Learning—0
Stabilized Likelihood-based Imitation Learning via Denoising Continuous Normalizing Flow—0
Imitation Learning from Pixel Observations for Continuous Control—0
What Would the Expert do()?: Causal Imitation Learning—0
Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts—0
DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations—0
Meta-Imitation Learning by Watching Video Demonstrations—0
Benchmarking Sample Selection Strategies for Batch Reinforcement Learning—0
CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games—0
Language Model Pre-training Improves Generalization in Policy Learning—0
Distributional Decision Transformer for Hindsight Information Matching—0
Show:102550
← PrevPage 52 of 85Next →

No leaderboard results yet.