Efficient Exploration

Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.

Source: Randomized Value Functions via Multiplicative Normalizing Flows

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 376–400 of 514 papers

Title	Date	Tasks	Status	Hype
Efficient exploration of zero-sum stochastic games	Feb 24, 2020	Efficient ExplorationThompson Sampling	—Unverified	0
Particle Filter Based Monocular Human Tracking with a 3D Cardbox Model and a Novel Deterministic Resampling Strategy	Feb 21, 2020	Efficient Exploration	—Unverified	0
Misspecification-robust likelihood-free inference in high dimensions	Feb 21, 2020	Bayesian OptimisationEfficient Exploration	—Unverified	0
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization	Feb 6, 2020	Efficient ExplorationOff-policy evaluation	—Unverified	0
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling	Jan 22, 2020	Decision MakingEfficient Exploration	CodeCode Available	0
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies	Jan 1, 2020	Efficient ExplorationMeta Reinforcement Learning	CodeCode Available	1
Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning	Dec 23, 2019	Efficient Explorationreinforcement-learning	CodeCode Available	0
Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning	Dec 13, 2019	continuous-controlContinuous Control	—Unverified	0
Provably Efficient Exploration in Policy Optimization	Dec 12, 2019	Efficient ExplorationReinforcement Learning	—Unverified	0
Explicit Planning for Efficient Exploration in Reinforcement Learning	Dec 1, 2019	Efficient Explorationreinforcement-learning	—Unverified	0
Better Exploration with Optimistic Actor Critic	Dec 1, 2019	continuous-controlContinuous Control	CodeCode Available	0
Comprehensive decision-strategy space exploration for efficient territorial planning strategies	Nov 26, 2019	Efficient Exploration	—Unverified	0
Scaling active inference	Nov 24, 2019	Efficient ExplorationReinforcement Learning	—Unverified	0
Bayesian Curiosity for Efficient Exploration in Reinforcement Learning	Nov 20, 2019	Efficient Explorationreinforcement-learning	CodeCode Available	0
Implicit Generative Modeling for Efficient Exploration	Nov 19, 2019	Efficient ExplorationFuture prediction	—Unverified	0
Efficient Exploration through Intrinsic Motivation Learning for Unsupervised Subgoal Discovery in Model-Free Hierarchical Reinforcement Learning	Nov 18, 2019	Efficient ExplorationHierarchical Reinforcement Learning	—Unverified	0
Neural Contextual Bandits with UCB-based Exploration	Nov 11, 2019	Efficient ExplorationMulti-Armed Bandits	CodeCode Available	0
Multi-Path Policy Optimization	Nov 11, 2019	Deep Reinforcement LearningEfficient Exploration	—Unverified	0
MAME : Model-Agnostic Meta-Exploration	Nov 11, 2019	Efficient ExplorationMeta Reinforcement Learning	—Unverified	0
Structured exploration in the finite horizon linear quadratic dual control problem	Oct 31, 2019	Efficient Exploration	—Unverified	0
VASE: Variational Assorted Surprise Exploration for Reinforcement Learning	Oct 31, 2019	continuous-controlContinuous Control	—Unverified	0
Better Exploration with Optimistic Actor-Critic	Oct 28, 2019	continuous-controlContinuous Control	—Unverified	0
Learning Transferable Graph Exploration	Oct 28, 2019	Efficient ExplorationReinforcement Learning	—Unverified	0
Dynamic Subgoal-based Exploration via Bayesian Optimization	Oct 21, 2019	Bayesian OptimizationEfficient Exploration	CodeCode Available	0
ConEx: Efficient Exploration of Big-Data System Configurations for Better Performance	Oct 17, 2019	Efficient Exploration	CodeCode Available	0

Show:10 25 50

← PrevPage 16 of 21Next →

No leaderboard results yet.