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
Non-Parallel Text Style Transfer with Self-Parallel SupervisionCode0
Divide & Conquer Imitation LearningCode0
Evaluating the Effectiveness of Corrective Demonstrations and a Low-Cost Sensor for Dexterous ManipulationCode0
Understanding Game-Playing Agents with Natural Language AnnotationsCode0
Causal Confusion and Reward Misidentification in Preference-Based Reward Learning—0
When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?—0
Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning—0
Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale—0
Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation Learning—0
Learning Generalizable Dexterous Manipulation from Human Grasp Affordance—0
Information-Theoretic Policy Learning from Partial Observations with Fully Informed Decision Makers—0
Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language GenerationCode0
Accelerating Federated Edge Learning via Topology Optimization—0
ReIL: A Framework for Reinforced Intervention-based Imitation Learning—0
Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task DivisionCode0
Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation—0
Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers—0
Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation—0
Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning—0
Self-Imitation Learning from Demonstrations—0
Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation—0
Causal Robot Communication Inspired by Observational Learning Insights—0
An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models—0
Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging taskCode0
Policy Architectures for Compositional Generalization in Control—0
Show:102550
← PrevPage 52 of 85Next →

No leaderboard results yet.