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 2611–2620 of 15113 papers

TitleStatusHype
Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains—0
Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning—0
FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots—0
Design and Experimental Test of Datatic Approximate Optimal Filter in Nonlinear Dynamic Systems—0
X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real—0
Learning Value of Information towards Joint Communication and Control in 6G V2X—0
Reinforcement Learning (RL) Meets Urban Climate Modeling: Investigating the Efficacy and Impacts of RL-Based HVAC Control—0
Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving—0
LineFlow: A Framework to Learn Active Control of Production LinesCode0
REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback—0
Show:102550
← PrevPage 262 of 1512Next →

Benchmark Results

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