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 51–75 of 15113 papers

TitleStatusHype
IRanker: Towards Ranking Foundation ModelCode1
Complex Model Transformations by Reinforcement Learning with Uncertain Human GuidanceCode0
Reinforcement Learning Increases Wind Farm Power Production by Enabling Closed-Loop Collaborative ControlCode0
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code GenerationCode4
OctoThinker: Mid-training Incentivizes Reinforcement Learning ScalingCode2
Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards—0
Partially Observable Residual Reinforcement Learning for PV-Inverter-Based Voltage Control in Distribution GridsCode0
KnowRL: Exploring Knowledgeable Reinforcement Learning for FactualityCode1
A Comparative Analysis of Reinforcement Learning and Conventional Deep Learning Approaches for Bearing Fault Diagnosis—0
Causal-Aware Intelligent QoE Optimization for VR Interaction with Adaptive Keyframe Extraction—0
Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion—0
Robots and Children that Learn Together : Improving Knowledge Retention by Teaching Peer-Like Interactive Robots—0
AdapThink: Adaptive Thinking Preferences for Reasoning Language Model—0
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement LearningCode5
Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics LearningCode2
Graphs Meet AI Agents: Taxonomy, Progress, and Future OpportunitiesCode2
Accelerating Residual Reinforcement Learning with Uncertainty Estimation—0
Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking—0
Learning Dexterous Object Handover—0
Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy EvaluationCode0
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using SparsityCode0
Multi-Task Lifelong Reinforcement Learning for Wireless Sensor Networks—0
Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations—0
From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation—0
VRAIL: Vectorized Reward-based Attribution for Interpretable Learning—0
Show:102550
← PrevPage 3 of 605Next →

Benchmark Results

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