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
Distributional Perturbation for Efficient Exploration in Distributional Reinforcement Learning—0
Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning—0
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning—0
Emotion-Agent: Unsupervised Deep Reinforcement Learning with Distribution-Prototype Reward for Continuous Emotional EEG Analysis—0
Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning—0
Bandit Algorithms for Tree Search—0
Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning—0
Efficient Robotic Object Search via HIEM: Hierarchical Policy Learning with Intrinsic-Extrinsic Modeling—0
Reinforcement Learning for Causal Discovery without Acyclicity Constraints—0
Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization—0
Embodied Agents for Efficient Exploration and Smart Scene Description—0
Entropic Risk-Sensitive Reinforcement Learning: A Meta Regret Framework with Function Approximation—0
Bag of Policies for Distributional Deep Exploration—0
Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science—0
A Human Mixed Strategy Approach to Deep Reinforcement Learning—0
Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model—0
A Web-scale system for scientific knowledge exploration—0
Efficient Policy Space Response Oracles—0
Contextual Decision Processes with Low Bellman Rank are PAC-Learnable—0
Context-Dependent Upper-Confidence Bounds for Directed Exploration—0
Active Model Estimation in Markov Decision Processes—0
Constrained Hybrid Metaheuristic Algorithm for Probabilistic Neural Networks Learning—0
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation—0
ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization—0
Efficient Informed Proposals for Discrete Distributions via Newton's Series Approximation—0
Show:102550
← PrevPage 6 of 21Next →

No leaderboard results yet.