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

Showing 131140 of 514 papers

TitleStatusHype
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal BabblingCode0
Personalized Algorithmic Recourse with Preference ElicitationCode0
Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?Code0
Generalization and Exploration via Randomized Value FunctionsCode0
GenPlan: Generative Sequence Models as Adaptive PlannersCode0
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement LearningCode0
EXPODE: EXploiting POlicy Discrepancy for Efficient Exploration in Multi-agent Reinforcement LearningCode0
Feature Interaction Aware Automated Data Representation TransformationCode0
Federated Control with Hierarchical Multi-Agent Deep Reinforcement LearningCode0
Dynamic Subgoal-based Exploration via Bayesian OptimizationCode0
Show:102550
← PrevPage 14 of 52Next →

No leaderboard results yet.