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 551–575 of 2122 papers

TitleStatusHype
Grounding Language Plans in Demonstrations Through Counterfactual Perturbations—0
Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination—0
Interpretable Modeling of Deep Reinforcement Learning Driven Scheduling—0
IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History—0
Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but ImprovementCode1
Automated Feature Selection for Inverse Reinforcement Learning—0
Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium ProofCode0
Augmented Reality Demonstrations for Scalable Robot Imitation Learning—0
Information-Theoretic Distillation for Reference-less Summarization—0
What AIs are not Learning (and Why)—0
Adaptive Visual Imitation Learning for Robotic Assisted Feeding Across Varied Bowl Configurations and Food Types—0
Offline Imitation of Badminton Player Behavior via Experiential Contexts and Brownian Motion—0
AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents—0
Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight—0
VITaL Pretraining: Visuo-Tactile Pretraining for Tactile and Non-Tactile Manipulation Policies—0
Supervised Fine-Tuning as Inverse Reinforcement Learning—0
SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy—0
DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation—0
TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation—0
Physics-informed Neural Motion Planning on Constraint Manifolds—0
Efficient Data Collection for Robotic Manipulation via Compositional Generalization—0
Globally Stable Neural Imitation PoliciesCode1
Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation—0
3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D RepresentationsCode5
Behavior Generation with Latent ActionsCode3
Show:102550
← PrevPage 23 of 85Next →

No leaderboard results yet.