SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–360 of 514 papers

TitleStatusHype
Bandit Algorithms for Tree Search—0
BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale—0
Bayesian optimisation of large-scale photonic reservoir computers—0
Bayesian optimization of distributed neurodynamical controller models for spatial navigation—0
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems—0
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems—0
β-DQN: Improving Deep Q-Learning By Evolving the Behavior—0
Better Exploration with Optimistic Actor-Critic—0
Beyond Games: Bringing Exploration to Robots in Real-world—0
Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning—0
Show:102550
← PrevPage 36 of 52Next →

No leaderboard results yet.