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 1326–1350 of 2122 papers

TitleStatusHype
Challenging Common Assumptions in Convex Reinforcement Learning—0
Practical Imitation Learning in the Real World via Task Consistency Loss—0
Yordle: An Efficient Imitation Learning for Branch and Bound—0
A General, Evolution-Inspired Reward Function for Social RoboticsCode0
Adversarial Imitation Learning from Video using a State Observer—0
Robust Imitation Learning from Corrupted Demonstrations—0
Transfering Hierarchical Structure with Dual Meta Imitation Learning—0
Burst-dependent plasticity and dendritic amplification support target-based learning and hierarchical imitation learningCode0
Reinforcement Routing on Proximity Graph for Efficient Recommendation—0
Ray Based Distributed Autonomous Vehicle Research Platform—0
Rethinking ValueDice: Does It Really Improve Performance?—0
An Improved Reinforcement Learning Algorithm for Learning to Branch—0
Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets—0
STIR^2: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks—0
Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents—0
Conditional Imitation Learning for Multi-Agent Games—0
Robust Entropy-regularized Markov Decision Processes—0
Stochastic convex optimization for provably efficient apprenticeship learning—0
Parallelized and Randomized Adversarial Imitation Learning for Safety-Critical Self-Driving Vehicles—0
Amortized Noisy Channel Neural Machine Translation—0
Modeling Strong and Human-Like Gameplay with KL-Regularized Search—0
Learning to Guide and to Be Guided in the Architect-Builder ProblemCode0
Probability Density Estimation Based Imitation Learning—0
Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample EfficiencyCode0
Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation—0
Show:102550
← PrevPage 54 of 85Next →

No leaderboard results yet.