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 1401–1450 of 2122 papers

TitleStatusHype
X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real—0
Yordle: An Efficient Imitation Learning for Branch and Bound—0
You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations—0
Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost—0
Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation—0
Zero-shot Imitation Policy via Search in Demonstration Dataset—0
Zero-shot Task Adaptation using Natural Language—0
Zero-Shot Transfer in Imitation Learning—0
Zero-Shot Visual Generalization in Robot Manipulation—0
Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Network—0
Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion—0
Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance—0
Learning a Decision Module by Imitating Driver's Control Behaviors—0
Learning Dynamic Graph for Overtaking Strategy in Autonomous Driving—0
Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future—0
Learning Effective Exploration Strategies For Contextual Bandits—0
Learning Efficient Planning-based Rewards for Imitation Learning—0
A Study of Learning Search Approximation in Mixed Integer Branch and Bound: Node Selection in SCIP—0
Learning energy-efficient driving behaviors by imitating experts—0
Learning Energy Networks with Generalized Fenchel-Young Losses—0
Learning Environment for the Air Domain (LEAD)—0
Learning Equational Theorem Proving—0
Learning Existing Social Conventions via Observationally Augmented Self-Play—0
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware—0
Learning Finite State Representations of Recurrent Policy Networks—0
Learning from Demonstrations of Critical Driving Behaviours Using Driver's Risk Field—0
Learning from Demonstrations with Energy based Generative Adversarial Imitation Learning—0
Validity Learning on Failures: Mitigating the Distribution Shift in Autonomous Vehicle Planning—0
Learning from Noisy Demonstration Sets via Meta-Learned Suitability Assessor—0
Learning Generalizable Dexterous Manipulation from Human Grasp Affordance—0
Learning Generalizable Manipulation Policies with Object-Centric 3D Representations—0
Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts—0
Learning Graph Search Heuristics—0
Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation—0
Learning Long-Context Diffusion Policies via Past-Token Prediction—0
Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation—0
Learning Modular Robot Locomotion from Demonstrations—0
Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach—0
Learning Multi-Arm Manipulation Through Collaborative Teleoperation—0
Learning Multi-Stage Tasks with One Demonstration via Self-Replay—0
Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning—0
Learning Neural Parsers with Deterministic Differentiable Imitation Learning—0
Learning Norms from Stories: A Prior for Value Aligned Agents—0
Learning Novel Skills from Language-Generated Demonstrations—0
Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics—0
Learning Perception-Aware Agile Flight in Cluttered Environments—0
Learning Policy Representations in Multiagent Systems—0
Learning Realistic Traffic Agents in Closed-loop—0
Learning Relative Interactions through Imitation—0
Learning Robotic Ultrasound Scanning Skills via Human Demonstrations and Guided Explorations—0
Show:102550
← PrevPage 29 of 43Next →

No leaderboard results yet.