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 21–30 of 514 papers

TitleStatusHype
Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning—0
Maya: Optimizing Deep Learning Training Workloads using Emulated Virtual Accelerators—0
FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs—0
CAE: Repurposing the Critic as an Explorer in Deep Reinforcement Learning—0
KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies—0
Disentangling Uncertainties by Learning Compressed Data RepresentationCode0
Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model—0
HyperArm Bandit Optimization: A Novel approach to Hyperparameter Optimization and an Analysis of Bandit Algorithms in Stochastic and Adversarial Settings—0
Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration—0
Reward-Centered ReST-MCTS: A Robust Decision-Making Framework for Robotic Manipulation in High Uncertainty EnvironmentsCode0
Show:102550
← PrevPage 3 of 52Next →

No leaderboard results yet.