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 1301–1325 of 2122 papers

TitleStatusHype
Towards Fusing Point Cloud and Visual Representations for Imitation Learning—0
Towards Human-Like Driving: Active Inference in Autonomous Vehicle Control—0
Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds—0
Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning—0
Towards More Generalizable One-shot Visual Imitation Learning—0
Towards Scalable Imitation Learning for Multi-Agent Systems with Graph Neural Networks—0
Toward the Fundamental Limits of Imitation Learning—0
Tracking the Race Between Deep Reinforcement Learning and Imitation Learning -- Extended Version—0
TRAIL: Near-Optimal Imitation Learning with Suboptimal Data—0
Training Electric Vehicle Charging Controllers with Imitation Learning—0
Training Neural Network Controllers Using Control Barrier Functions in the Presence of Disturbances—0
Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer—0
Trajectory VAE for multi-modal imitation—0
Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble—0
Transfering Hierarchical Structure with Dual Meta Imitation Learning—0
Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges—0
Transferring Hierarchical Structure with Dual Meta Imitation Learning—0
Transfer RL via the Undo Maps Formalism—0
Transformer-based deep imitation learning for dual-arm robot manipulation—0
Transformers for One-Shot Visual Imitation—0
Translating Natural Language Instructions to Computer Programs for Robot Manipulation—0
Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks—0
Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets—0
Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning—0
Tube-NeRF: Efficient Imitation Learning of Visuomotor Policies from MPC using Tube-Guided Data Augmentation and NeRFs—0
Show:102550
← PrevPage 53 of 85Next →

No leaderboard results yet.