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 951–975 of 2122 papers

TitleStatusHype
Progressively Efficient Learning—0
Cross-Episodic Curriculum for Transformer Agents—0
Generative Intrinsic Optimization: Intrinsic Control with Model Learning—0
Imitation Learning from Purified DemonstrationsCode0
Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning—0
Zero-Shot Transfer in Imitation Learning—0
Inverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning—0
Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments—0
Memory-Consistent Neural Networks for Imitation Learning—0
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models—0
Offline Imitation Learning with Variational Counterfactual ReasoningCode0
STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent—0
Blending Imitation and Reinforcement Learning for Robust Policy Improvement—0
Imitation Learning from Observation through Optimal Transport—0
Interpretable Imitation Learning with Dynamic Causal Relations—0
Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Network—0
Adversarial Imitation Learning from Visual Observations using Latent InformationCode0
Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning—0
CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture—0
Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies—0
Hierarchical Imitation Learning for Stochastic Environments—0
Offline to Online Learning for Real-Time Bandwidth Estimation—0
Improving Generalization in Game Agents with Data Augmentation in Imitation Learning—0
Learning to Drive Anywhere—0
Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting Robots—0
Show:102550
← PrevPage 39 of 85Next →

No leaderboard results yet.