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 2201–2210 of 15113 papers

TitleStatusHype
Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts—0
SmartPathfinder: Pushing the Limits of Heuristic Solutions for Vehicle Routing Problem with Drones Using Reinforcement Learning—0
WROOM: An Autonomous Driving Approach for Off-Road NavigationCode1
Dataset Reset Policy Optimization for RLHFCode1
Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement LearningCode0
Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation—0
FPGA Divide-and-Conquer Placement using Deep Reinforcement Learning—0
Enhancing Policy Gradient with the Polyak Step-Size Adaption—0
Efficient Duple Perturbation Robustness in Low-rank MDPs—0
Leveraging Domain-Unlabeled Data in Offline Reinforcement Learning across Two Domains—0
Show:102550
← PrevPage 221 of 1512Next →

Benchmark Results

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