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 1126–1150 of 2122 papers

TitleStatusHype
NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis—0
Adaptive Neural Networks Using Residual Fitting—0
Explaining Imitation Learning through Frames—0
Genetic Imitation Learning by Reward Extrapolation—0
RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension—0
Imitation Learning As State Matching via Differentiable Physics—0
Bayesian Learning for Dynamic Inference—0
Behavioral Cloning via Search in Video PreTraining Latent Space—0
Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios—0
I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation—0
Model-based trajectory stitching for improved behavioural cloning and its applications—0
Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble—0
Learning Graph Search Heuristics—0
Efficient Learning of Voltage Control Strategies via Model-based Deep Reinforcement Learning—0
Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible RobotsCode0
Learning to Optimize in Model Predictive Control—0
Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations—0
Learning and Blending Robot Hugging Behaviors in Time and Space—0
Generalizable Human-Robot Collaborative Assembly Using Imitation Learning and Force Control—0
Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula—0
Safe Reinforcement Learning with Probabilistic Control Barrier Functions for Ramp Merging—0
Multi-Task Imitation Learning for Linear Dynamical Systems—0
Towards Improving Exploration in Self-Imitation Learning using Intrinsic MotivationCode0
Transfer RL via the Undo Maps Formalism—0
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning—0
Show:102550
← PrevPage 46 of 85Next →

No leaderboard results yet.