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 3071–3080 of 15113 papers

TitleStatusHype
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking—0
Exploring the Technology Landscape through Topic Modeling, Expert Involvement, and Reinforcement Learning—0
Adaptive Data Exploitation in Deep Reinforcement LearningCode0
On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration—0
Reinforcement learning Based Automated Design of Differential Evolution Algorithm for Black-box Optimization—0
State Combinatorial Generalization In Decision Making With Conditional Diffusion Models—0
Evolution and The Knightian Blindspot of Machine Learning—0
To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement LearningCode0
Deep Reinforcement Learning with Hybrid Intrinsic Reward Model—0
AdaWM: Adaptive World Model based Planning for Autonomous Driving—0
Show:102550
← PrevPage 308 of 1512Next →

Benchmark Results

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