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 311–320 of 514 papers

TitleStatusHype
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement LearningCode0
Discovering and Exploiting Sparse Rewards in a Learned Behavior SpaceCode0
Bayesian optimization of distributed neurodynamical controller models for spatial navigation—0
Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives—0
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and GeneralizationCode0
Map Induction: Compositional spatial submap learning for efficient exploration in novel environmentsCode0
More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences—0
Balancing Value Underestimation and Overestimation with Realistic Actor-CriticCode0
Efficient Exploration in Binary and Preferential Bayesian Optimization—0
Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization—0
Show:102550
← PrevPage 32 of 52Next →

No leaderboard results yet.