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 2761–2770 of 15113 papers

TitleStatusHype
De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning—0
Probabilistic Curriculum Learning for Goal-Based Reinforcement Learning—0
Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning—0
Value Iteration for Learning Concurrently Executable Robotic Control TasksCode0
How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study—0
Fair Dynamic Spectrum Access via Fully Decentralized Multi-Agent Reinforcement Learning—0
A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective—0
Accelerating High-Efficiency Organic Photovoltaic Discovery via Pretrained Graph Neural Networks and Generative Reinforcement Learning—0
Noise-based reward-modulated learning—0
JudgeLRM: Large Reasoning Models as a Judge—0
Show:102550
← PrevPage 277 of 1512Next →

Benchmark Results

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