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 1526–1550 of 2122 papers

TitleStatusHype
Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations—0
Mastering Contact-rich Tasks by Combining Soft and Rigid Robotics with Imitation Learning—0
Mature GAIL: Imitation Learning for Low-level and High-dimensional Input using Global Encoder and Cost Transformation—0
Maximum Causal Tsallis Entropy Imitation Learning—0
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees—0
MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed—0
MDPFuzz: Testing Models Solving Markov Decision Processes—0
DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation—0
Memory-based gaze prediction in deep imitation learning for robot manipulation—0
Memory-Consistent Neural Networks for Imitation Learning—0
MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention—0
Meta Adaptation using Importance Weighted Demonstrations—0
Meta-Imitation Learning by Watching Video Demonstrations—0
Meta-Learning for Contextual Bandit Exploration—0
Meta learning Framework for Automated Driving—0
Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles—0
Meta-Reinforcement Learning for Mastering Multiple Skills and Generalizing across Environments in Text-based Games—0
MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization—0
MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility—0
Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms—0
MILE: Model-based Intervention Learning—0
MILES: Making Imitation Learning Easy with Self-Supervision—0
MILP-based Imitation Learning for HVAC control—0
MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl—0
Mimicking actions is a good strategy for beginners: Fast Reinforcement Learning with Expert Action Sequences—0
Show:102550
← PrevPage 62 of 85Next →

No leaderboard results yet.