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 291–300 of 514 papers

TitleStatusHype
Map Induction: Compositional spatial submap learning for efficient exploration in novel environmentsCode0
Hierarchical Skills for Efficient ExplorationCode1
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
Reinforcement Learning in Reward-Mixing MDPs—0
Divide and Explore: Multi-Agent Separate Exploration with Shared Intrinsic Motivations—0
Learning to Solve Combinatorial Problems via Efficient Exploration—0
HyperDQN: A Randomized Exploration Method for Deep Reinforcement LearningCode1
Show:102550
← PrevPage 30 of 52Next →

No leaderboard results yet.