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 661–670 of 2122 papers

TitleStatusHype
Few-Shot Bayesian Imitation Learning with Logical Program Policies—0
Few-Shot In-Context Imitation Learning via Implicit Graph Alignment—0
Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation—0
Generalizable Imitation Learning Through Pre-Trained Representations—0
Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts—0
Fighting Copycat Agents in Behavioral Cloning from Observation Histories—0
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming—0
Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching—0
Generalizing to New Tasks via One-Shot Compositional Subgoals—0
Generative Adversarial Self-Imitation Learning—0
Show:102550
← PrevPage 67 of 213Next →

No leaderboard results yet.