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 281–290 of 514 papers

TitleStatusHype
Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and ExplorationsCode0
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks—0
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks—0
The split Gibbs sampler revisited: improvements to its algorithmic structure and augmented target distributionCode0
GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning—0
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation—0
Scalable Exploration for Neural Online Learning to Rank with Perturbed Feedback—0
Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems—0
On Preemption and Learning in Stochastic SchedulingCode0
Personalized Algorithmic Recourse with Preference ElicitationCode0
Show:102550
← PrevPage 29 of 52Next →

No leaderboard results yet.