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 101–110 of 514 papers

TitleStatusHype
Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation—0
DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models—0
FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching—0
Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts—0
Massively Scaling Explicit Policy-conditioned Value Functions—0
Causal Information Prioritization for Efficient Reinforcement Learning—0
Exploratory Diffusion Model for Unsupervised Reinforcement Learning—0
Guided Exploration for Efficient Relational Model Learning—0
Few-shot_LLM_Synthetic_Data_with_Distribution_MatchingCode0
Adaptive Exploration for Multi-Reward Multi-Policy Evaluation—0
Show:102550
← PrevPage 11 of 52Next →

No leaderboard results yet.