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 1476–1500 of 2122 papers

TitleStatusHype
Active Third-Person Imitation Learning—0
ACT-JEPA: Joint-Embedding Predictive Architecture Improves Policy Representation Learning—0
AdaCred: Adaptive Causal Decision Transformers with Feature Crediting—0
AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent—0
ADAIL: Adaptive Adversarial Imitation Learning—0
AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning—0
Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning—0
Adapting a World Model for Trajectory Following in a 3D Game—0
Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence—0
Adaptive Adversarial Imitation Learning—0
Adaptive Neural Networks Using Residual Fitting—0
Adaptive Synthetic Characters for Military Training—0
Adaptive t-Momentum-based Optimization for Unknown Ratio of Outliers in Amateur Data in Imitation Learning—0
Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types—0
Addressing Limitations of State-Aware Imitation Learning for Autonomous Driving—0
A Dual Approach to Imitation Learning from Observations with Offline Datasets—0
Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning—0
Adversarial Exploitation of Policy Imitation—0
Adversarial Active Exploration for Inverse Dynamics Model Learning—0
Adversarial Exploration Strategy for Self-Supervised Imitation Learning—0
Adversarial Imitation Learning from Video using a State Observer—0
Adversarial Imitation Learning On Aggregated Data—0
Adversarial Imitation Learning via Boosting—0
Adversarial Imitation Learning via Random Search—0
Decision Making for Autonomous Driving via Augmented Adversarial Inverse Reinforcement Learning—0
Show:102550
← PrevPage 60 of 85Next →

No leaderboard results yet.