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 2101–2110 of 2122 papers

TitleStatusHype
Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning—0
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models—0
Infinite-Horizon Differentiable Model Predictive Control—0
Information-Theoretic Distillation for Reference-less Summarization—0
Information-Theoretic Policy Learning from Partial Observations with Fully Informed Decision Makers—0
Initial State Interventions for Deconfounded Imitation Learning—0
Inspiration Learning through Preferences—0
Instant Policy: In-Context Imitation Learning via Graph Diffusion—0
Integrating Learning-Based Manipulation and Physics-Based Locomotion for Whole-Body Badminton Robot Control—0
Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model—0
Show:102550
← PrevPage 211 of 213Next →

No leaderboard results yet.