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 126–150 of 514 papers

TitleStatusHype
Randomized-Grid Search for Hyperparameter Tuning in Decision Tree Model to Improve Performance of Cardiovascular Disease Classification—0
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem SolvingCode0
Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problemsCode0
Learning Dynamic Cognitive Map with Autonomous NavigationCode0
Scalable Sampling for High Utility PatternsCode0
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL—0
EfficientEQA: An Efficient Approach for Open Vocabulary Embodied Question Answering—0
Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration—0
Scattered Forest Search: Smarter Code Space Exploration with LLMs—0
TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement LearningCode0
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning—0
Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task ComplexityCode0
Latent Action Priors for Locomotion with Deep Reinforcement Learning—0
BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale—0
Adaptive teachers for amortized samplersCode0
Provably Efficient Exploration in Inverse Constrained Reinforcement Learning—0
QueryBuilder: Human-in-the-Loop Query Development for Information Retrieval—0
Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal GuidanceCode0
Targeting the partition function of chemically disordered materials with a generative approach based on inverse variational autoencoders—0
Reinforcement Learning for Causal Discovery without Acyclicity Constraints—0
Emotion-Agent: Unsupervised Deep Reinforcement Learning with Distribution-Prototype Reward for Continuous Emotional EEG Analysis—0
Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction—0
Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithm—0
Modeling Multi-Step Scientific Processes with Graph Transformer Networks—0
KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance—0
Show:102550
← PrevPage 6 of 21Next →

No leaderboard results yet.