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 101–125 of 514 papers

TitleStatusHype
Instance Temperature Knowledge DistillationCode0
ASCENT: Amplifying Power Side-Channel Resilience via Learning & Monte-Carlo Tree SearchCode0
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation—0
Efficient gPC-based quantification of probabilistic robustness for systems in neuroscience—0
Exploration by Learning Diverse Skills through Successor State Measures—0
OTO Planner: An Efficient Only Travelling Once Exploration Planner for Complex and Unknown EnvironmentsCode0
World Models with Hints of Large Language Models for Goal Achieving—0
Robust quantum dots charge autotuning using neural network uncertaintyCode0
Efficient Exploration of the Rashomon Set of Rule Set ModelsCode0
Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability ObjectivesCode0
NeoRL: Efficient Exploration for Nonepisodic RL—0
Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior SamplingCode0
Computing low-thrust transfers in the asteroid belt, a comparison between astrodynamical manipulations and a machine learning approach—0
Opinion-Guided Reinforcement Learning—0
Evolutionary Large Language Model for Automated Feature TransformationCode1
GLaD: Synergizing Molecular Graphs and Language Descriptors for Enhanced Power Conversion Efficiency Prediction in Organic Photovoltaic Devices—0
Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principle—0
Navigating Chemical Space with Latent FlowsCode1
MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure—0
Efficient Exploration of Image Classifier Failures with Bayesian Optimization and Text-to-Image Models—0
Evolutionary Reinforcement Learning via Cooperative Coevolution—0
An Offline Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems—0
Sampling for Model Predictive Trajectory Planning in Autonomous Driving using Normalizing Flows—0
Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization ApproachCode7
Learning Off-policy with Model-based Intrinsic Motivation For Active Online Exploration—0
Show:102550
← PrevPage 5 of 21Next →

No leaderboard results yet.