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 1251–1260 of 15113 papers

TitleStatusHype
Reinforcement learning-enhanced genetic algorithm for wind farm layout optimization—0
From Laws to Motivation: Guiding Exploration through Law-Based Reasoning and Rewards—0
Broad Critic Deep Actor Reinforcement Learning for Continuous Control—0
Learning a local trading strategy: deep reinforcement learning for grid-scale renewable energy integration—0
Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward—0
Enhancing Molecular Design through Graph-based Topological Reinforcement Learning—0
Segmenting Action-Value Functions Over Time-Scales in SARSA via TD(Δ)—0
Free Energy Projective Simulation (FEPS): Active inference with interpretability—0
GraCo -- A Graph Composer for Integrated Circuits—0
Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problemsCode0
Show:102550
← PrevPage 126 of 1512Next →

Benchmark Results

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