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 231–240 of 514 papers

TitleStatusHype
Inferring Hierarchical Structure in Multi-Room Maze Environments—0
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP—0
A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning—0
PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm—0
Magnitude Attention-based Dynamic Pruning—0
Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial OptimizationCode0
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search—0
Large-Batch, Iteration-Efficient Neural Bayesian Design OptimizationCode0
EXPODE: EXploiting POlicy Discrepancy for Efficient Exploration in Multi-agent Reinforcement LearningCode0
Successor-Predecessor Intrinsic Exploration—0
Show:102550
← PrevPage 24 of 52Next →

No leaderboard results yet.