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 1901–1950 of 2122 papers

TitleStatusHype
Atari-HEAD: Atari Human Eye-Tracking and Demonstration DatasetCode1
Toward Imitating Visual Attention of Experts in Software Development Tasks—0
Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation LearningCode0
Imitation Learning of Factored Multi-agent Reactive Models—0
Hybrid Reinforcement Learning with Expert State SequencesCode0
Dyna-AIL : Adversarial Imitation Learning by Planning—0
Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future—0
Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives—0
Learning Exploration Policies for NavigationCode1
MGpi: A Computational Model of Multiagent Group Perception and InteractionCode0
Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware PerspectiveCode0
GRP Model for Sensorimotor Learning—0
Learning Dynamic-Objective Policies from a Class of Optimal Trajectories—0
Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement LearningCode0
Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup—0
Artificial Intelligence for Prosthetics - challenge solutionsCode0
Decentralized Multi-Agents by Imitation of a Centralized Controller—0
Non-Monotonic Sequential Text GenerationCode0
NAOMI: Non-Autoregressive Multiresolution Sequence ImputationCode1
Go-Explore: a New Approach for Hard-Exploration ProblemsCode1
Imitation Learning from Imperfect Demonstration—0
Evaluation Function Approximation for Scrabble—0
Meta-Learning for Contextual Bandit Exploration—0
Hierarchical Reinforcement Learning for Multi-agent MOBA Game—0
Towards Learning to Imitate from a Single Video Demonstration—0
Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission ExecutionCode0
Transfer Learning for Prosthetics Using Imitation LearningCode0
On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator—0
Learning the optimal state-feedback via supervised imitation learning—0
LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples—0
Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera—0
Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect InterventionCode0
Dialogue Generation: From Imitation Learning to Inverse Reinforcement LearningCode0
ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the WorstCode0
On the stability analysis of deep neural network representations of an optimal state-feedbackCode0
CompILE: Compositional Imitation Learning and ExecutionCode0
Generative Adversarial Self-Imitation Learning—0
A Bayesian Approach to Generative Adversarial Imitation Learning—0
Exponentially Weighted Imitation Learning for Batched Historical Data—0
Discovering hierarchies using Imitation Learning from hierarchy aware policies—0
BlockPuzzle - A Challenge in Physical Reasoning and Generalization for Robot Learning—0
Learning Finite State Representations of Recurrent Policy Networks—0
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation—0
Connecting the Dots Between MLE and RL for Sequence Prediction—0
Early Fusion for Goal Directed Robotic Vision—0
Guiding Policies with Language via Meta-LearningCode0
An Algorithmic Perspective on Imitation Learning—0
Reward learning from human preferences and demonstrations in AtariCode0
Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy—0
Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation PredictionCode0
Show:102550
← PrevPage 39 of 43Next →

No leaderboard results yet.