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 291–300 of 514 papers

TitleStatusHype
Scalable Exploration for Neural Online Learning to Rank with Perturbed Feedback—0
Scaling active inference—0
Scattered Forest Search: Smarter Code Space Exploration with LLMs—0
Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning—0
Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning—0
SEMI: Self-supervised Exploration via Multisensory Incongruity—0
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models—0
SHIRO: Soft Hierarchical Reinforcement Learning—0
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks—0
Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution—0
Show:102550
← PrevPage 30 of 52Next →

No leaderboard results yet.