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 476–500 of 514 papers

TitleStatusHype
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement LearningCode0
OTO Planner: An Efficient Only Travelling Once Exploration Planner for Complex and Unknown EnvironmentsCode0
Uncertainty-Guided Optimization on Large Language Model Search TreesCode0
Model-based Reinforcement Learning for Continuous Control with Posterior SamplingCode0
Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement LearningCode0
A Gradient Sampling Algorithm for Stratified Maps with Applications to Topological Data AnalysisCode0
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement LearningCode0
Parameterized Indexed Value Function for Efficient Exploration in Reinforcement LearningCode0
Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial OptimizationCode0
Scalable Online Exploration via CoverabilityCode0
Learning to Act with Affordance-Aware Multimodal Neural SLAMCode0
Scalable Sampling for High Utility PatternsCode0
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem SolvingCode0
Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone MicrocontrollerCode0
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient ExplorationCode0
Bootstrapped Meta-LearningCode0
TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement LearningCode0
Disentangling Uncertainties by Learning Compressed Data RepresentationCode0
Playing Text-Adventure Games with Graph-Based Deep Reinforcement LearningCode0
LECO: Learnable Episodic Count for Task-Specific Intrinsic RewardCode0
Discovering and Exploiting Sparse Rewards in a Learned Behavior SpaceCode0
Bayesian Curiosity for Efficient Exploration in Reinforcement LearningCode0
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesisCode0
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement LearningCode0
Deep Exploration via Bootstrapped DQNCode0
Show:102550
← PrevPage 20 of 21Next →

No leaderboard results yet.