SOTAVerified|Agents Browse Leaderboard About

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 41–50 of 514 papers

Title	Date	Tasks	Status	Hype
NovelD: A Simple yet Effective Exploration Criterion	Dec 1, 2021	Atari GamesDeep Reinforcement Learning	CodeCode Available	1
Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration	Nov 22, 2021	Efficient ExplorationMulti-agent Reinforcement Learning	CodeCode Available	1
Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning	Oct 26, 2021	Efficient ExplorationHierarchical Reinforcement Learning	CodeCode Available	1
Hierarchical Skills for Efficient Exploration	Oct 20, 2021	continuous-controlContinuous Control	CodeCode Available	1
HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning	Sep 29, 2021	Deep Reinforcement LearningEfficient Exploration	CodeCode Available	1
Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning	Jul 30, 2021	Efficient ExplorationMulti-agent Reinforcement Learning	CodeCode Available	1
MADE: Exploration via Maximizing Deviation from Explored Regions	Jun 18, 2021	Efficient ExplorationReinforcement Learning (RL)	CodeCode Available	1
Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks	May 10, 2021	Efficient ExplorationMulti-Armed Bandits	CodeCode Available	1
Paradiseo: From a Modular Framework for Evolutionary Computation to the Automated Design of Metaheuristics ---22 Years of Paradiseo---	May 2, 2021	Efficient ExplorationMetaheuristic Optimization	CodeCode Available	1
State Entropy Maximization with Random Encoders for Efficient Exploration	Feb 18, 2021	Deep Reinforcement LearningEfficient Exploration	CodeCode Available	1

Show:10 25 50

← PrevPage 5 of 52Next →

No leaderboard results yet.