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 1631–1640 of 2122 papers

TitleStatusHype
Offline Imitation of Badminton Player Behavior via Experiential Contexts and Brownian Motion—0
Offline Inverse Reinforcement Learning—0
Offline Learning from Demonstrations and Unlabeled Experience—0
Offline Learning of Controllable Diverse Behaviors—0
Off-policy Imitation Learning from Visual Inputs—0
OIL: Observational Imitation Learning—0
OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation—0
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents—0
OmniRL: In-Context Reinforcement Learning by Large-Scale Meta-Training in Randomized Worlds—0
On Combining Expert Demonstrations in Imitation Learning via Optimal Transport—0
Show:102550
← PrevPage 164 of 213Next →

No leaderboard results yet.