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 701–725 of 2122 papers

TitleStatusHype
Exploring the trade off between human driving imitation and safety for traffic simulation—0
Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning—0
Co-Imitation: Learning Design and Behaviour by Imitation—0
GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback—0
GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts—0
Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective—0
A Strong Baseline for Batch Imitation Learning—0
Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks—0
Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation—0
Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)—0
A Statistical Guarantee for Representation Transfer in Multitask Imitation Learning—0
Action-Free Reasoning for Policy Generalization—0
Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning—0
Generalizable Human-Robot Collaborative Assembly Using Imitation Learning and Force Control—0
Generalizable Imitation Learning from Observation via Inferring Goal Proximity—0
Generalizable Imitation Learning Through Pre-Trained Representations—0
Generalization Capability for Imitation Learning—0
Exploration Based Language Learning for Text-Based Games—0
Explaining Imitation Learning through Frames—0
CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity—0
Generalized Robot Learning Framework—0
Generalizing to New Tasks via One-Shot Compositional Subgoals—0
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics—0
Generating Personas for Games with Multimodal Adversarial Imitation Learning—0
CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration—0
Show:102550
← PrevPage 29 of 85Next →

No leaderboard results yet.