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 1076–1100 of 2122 papers

TitleStatusHype
Learning Robot Manipulation from Cross-Morphology DemonstrationCode0
End-to-end Manipulator Calligraphy Planning via Variational Imitation Learning—0
ENTL: Embodied Navigation Trajectory Learner—0
Quantum Imitation Learning—0
Imitation Learning from Nonlinear MPC via the Exact Q-Loss and its Gauss-Newton Approximation—0
Generative Adversarial Neuroevolution for Control Behaviour ImitationCode0
MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from ObservationsCode0
Specification-Guided Data Aggregation for Semantically Aware Imitation Learning—0
Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costsCode0
Efficient Deep Learning of Robust, Adaptive Policies using Tube MPC-Guided Data Augmentation—0
Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse SkillsCode0
Exploring the use of deep learning in task-flexible ILC—0
Embedding Contextual Information through Reward Shaping in Multi-Agent Learning: A Case Study from Google Football—0
Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning—0
Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks—0
Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous Driving—0
Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale—0
Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum—0
Sample-efficient Adversarial Imitation Learning—0
Implicit and Explicit Commonsense for Multi-sentence Video Captioning—0
Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation—0
ConBaT: Control Barrier Transformer for Safe Policy Learning—0
Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching—0
Interactive Text Generation—0
MEGA-DAgger: Imitation Learning with Multiple Imperfect ExpertsCode0
Show:102550
← PrevPage 44 of 85Next →

No leaderboard results yet.