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 251–260 of 514 papers

TitleStatusHype
Opinion-Guided Reinforcement Learning—0
Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning—0
Optimization by Pairwise Linkage Detection, Incremental Linkage Set, and Restricted / Back Mixing: DSMGA-II—0
Optimizing Routerless Network-on-Chip Designs: An Innovative Learning-Based Framework—0
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL—0
PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm—0
ParamsDrag: Interactive Parameter Space Exploration via Image-Space Dragging—0
Particle Filter Based Monocular Human Tracking with a 3D Cardbox Model and a Novel Deterministic Resampling Strategy—0
PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning—0
Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction—0
Show:102550
← PrevPage 26 of 52Next →

No leaderboard results yet.