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 1251–1300 of 2122 papers

TitleStatusHype
Supervised Fine-Tuning as Inverse Reinforcement Learning—0
Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)—0
Support-guided Adversarial Imitation Learning—0
Support-weighted Adversarial Imitation Learning—0
Swarm Behavior Cloning—0
Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation—0
Symbolic Imitation Learning: From Black-Box to Explainable Driving Policies—0
Synthesizing Physical Character-Scene Interactions—0
Synthesizing Programmatic Policies that Inductively Generalize—0
Synthetically Generating Human-like Data for Sequential Decision Making Tasks via Reward-Shaped Imitation Learning—0
Tackling the Low-resource Challenge for Canonical Segmentation—0
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models—0
TamedPUMA: safe and stable imitation learning with geometric fabrics—0
TarGF: Learning Target Gradient Field to Rearrange Objects without Explicit Goal Specification—0
Task-Driven Semantic Quantization and Imitation Learning for Goal-Oriented Communications—0
Task-Induced Representation Learning—0
Task-Relevant Adversarial Imitation Learning—0
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models—0
TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation—0
Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation—0
TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation—0
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations—0
Tensor-based Cooperative Control for Large Scale Multi-intersection Traffic Signal Using Deep Reinforcement Learning and Imitation Learning—0
TextGAIL: Generative Adversarial Imitation Learning for Text Generation—0
The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI—0
The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner—0
The intrinsic motivation of reinforcement and imitation learning for sequential tasks—0
The MineRL BASALT Competition on Learning from Human Feedback—0
Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning—0
The Past and Present of Imitation Learning: A Citation Chain Study—0
The Pitfalls of Imitation Learning when Actions are Continuous—0
The Prevalence of Neural Collapse in Neural Multivariate Regression—0
The State-Action-Reward-State-Action Algorithm in Spatial Prisoner's Dilemma Game—0
The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning—0
The Virtuous Machine - Old Ethics for New Technology?—0
Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought—0
ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning—0
TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning—0
Time-Efficient Reinforcement Learning with Stochastic Stateful Policies—0
Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation—0
TLA: Tactile-Language-Action Model for Contact-Rich Manipulation—0
To Follow or not to Follow: Selective Imitation Learning from Observations—0
Tool-as-Interface: Learning Robot Policies from Human Tool Usage through Imitation Learning—0
Topological Navigation Graph Framework—0
Touch begins where vision ends: Generalizable policies for contact-rich manipulation—0
Toward Imitating Visual Attention of Experts in Software Development Tasks—0
Towards an Adaptable and Generalizable Optimization Engine in Decision and Control: A Meta Reinforcement Learning Approach—0
Towards a Reward-Free Reinforcement Learning Framework for Vehicle Control—0
Towards Data-Driven Automatic Video Editing—0
Towards Embodied Scene Description—0
Show:102550
← PrevPage 26 of 43Next →

No leaderboard results yet.