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 1851–1875 of 2122 papers

TitleStatusHype
Co-training for Policy LearningCode0
Active Learning within Constrained Environments through Imitation of an Expert Questioner—0
Sample Efficient Learning of Path Following and Obstacle Avoidance Behavior for Quadrotors—0
Supervise Thyself: Examining Self-Supervised Representations in Interactive EnvironmentsCode0
PyRep: Bringing V-REP to Deep Robot LearningCode0
Learning to Interactively Learn and Assist—0
Learning Belief Representations for Imitation Learning in POMDPsCode0
Wasserstein Adversarial Imitation Learning—0
Sample-efficient Adversarial Imitation Learning from Observation—0
RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstration—0
RadGrad: Active learning with loss gradients—0
Goal-conditioned Imitation LearningCode0
Imitation Learning of Neural Spatio-Temporal Point ProcessesCode0
Learning to Score Behaviors for Guided Policy OptimizationCode0
Watch, Try, Learn: Meta-Learning from Demonstrations and Reward—0
Multimodal End-to-End Autonomous Driving—0
An Imitation Learning Approach to Unsupervised ParsingCode0
Imitation Learning for Non-Autoregressive Neural Machine Translation—0
Simultaneous Translation with Flexible Policy via Restricted Imitation Learning—0
Towards Interactive Training of Non-Player Characters in Video GamesCode0
Adversarial Exploitation of Policy Imitation—0
Pay Attention! - Robustifying a Deep Visuomotor Policy Through Task-Focused Visual AttentionCode0
Imitation Learning as f-Divergence Minimization—0
Exploring Computational User Models for Agent Policy SummarizationCode0
On Value Functions and the Agent-Environment Boundary—0
Show:102550
← PrevPage 75 of 85Next →

No leaderboard results yet.