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 1451–1475 of 2122 papers

TitleStatusHype
Interactive Learning from Activity DescriptionCode0
Scalable Bayesian Inverse Reinforcement LearningCode1
Proof Artifact Co-training for Theorem Proving with Language ModelsCode1
Representation Matters: Offline Pretraining for Sequential Decision Making—0
Learning Equational Theorem Proving—0
Feedback in Imitation Learning: The Three Regimes of Covariate Shift—0
Hybrid Adversarial Imitation Learning—0
Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation—0
Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars—0
Learning Structural Edits via Incremental Tree TransformationsCode1
Embedding Symbolic Temporal Knowledge into Deep Sequential Models—0
MPC-MPNet: Model-Predictive Motion Planning Networks for Fast, Near-Optimal Planning under Kinodynamic ConstraintsCode1
EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of Vehicles—0
Adaptive Synthetic Characters for Military Training—0
Robust Maximum Entropy Behavior Cloning—0
SDA: Improving Text Generation with Self Data Augmentation—0
Self-Motivated Communication Agent for Real-World Vision-Dialog Navigation—0
CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning for Online Temporal Action Localization—0
Learning from Demonstrations with Energy based Generative Adversarial Imitation Learning—0
Scalable Bayesian Inverse Reinforcement Learning by Auto-Encoding Reward—0
Unbiased learning with State-Conditioned Rewards in Adversarial Imitation Learning—0
Goal-Driven Imitation Learning from Observation by Inferring Goal Proximity—0
Learning Efficient Planning-based Rewards for Imitation Learning—0
Learning to Search for Fast Maximum Common Subgraph Detection—0
Learning Task Decomposition with Order-Memory Policy Network—0
Show:102550
← PrevPage 59 of 85Next →

No leaderboard results yet.