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 631–640 of 2122 papers

TitleStatusHype
Active Hierarchical Imitation and Reinforcement Learning—0
Combining Imitation and Reinforcement Learning with Free Energy Principle—0
A survey of air combat behavior modeling using machine learning—0
Combating False Negatives in Adversarial Imitation Learning—0
Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning—0
A Study of Imitation Learning Methods for Semantic Role Labeling—0
COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy—0
Exponentially Weighted Imitation Learning for Batched Historical Data—0
Co-Imitation Learning without Expert Demonstration—0
Causal Confusion and Reward Misidentification in Preference-Based Reward Learning—0
Show:102550
← PrevPage 64 of 213Next →

No leaderboard results yet.