SOTAVerified

Reinforcement Learning (RL)

Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1981–1990 of 15113 papers

TitleStatusHype
REvolve: Reward Evolution with Large Language Models using Human Feedback—0
Federated Learning-based Collaborative Wideband Spectrum Sensing and Scheduling for UAVs in UTM Systems—0
MOSEAC: Streamlined Variable Time Step Reinforcement LearningCode0
Learning the Target Network in Function Space—0
Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programming—0
A Digital Twin Framework for Reinforcement Learning with Real-Time Self-Improvement via Human Assistive Teleoperation—0
FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement LearningCode1
Crafting a Pogo Stick in Minecraft with Heuristic Search (Extended Abstract)Code0
SUBER: An RL Environment with Simulated Human Behavior for Recommender SystemsCode1
Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling—0
Show:102550
← PrevPage 199 of 1512Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PPGMean Normalized Performance0.76—Unverified
2PPOMean Normalized Performance0.58—Unverified