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 226–250 of 15113 papers

TitleStatusHype
SOReL and TOReL: Two Methods for Fully Offline Reinforcement LearningCode0
Advancing Multimodal Reasoning via Reinforcement Learning with Cold StartCode1
Maximizing Confidence Alone Improves Reasoning—0
Decomposing Elements of Problem Solving: What "Math" Does RL Teach?Code0
Scaling Offline RL via Efficient and Expressive Shortcut Models—0
When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?Code0
SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning—0
Enhancing Study-Level Inference from Clinical Trial Papers via RL-based Numeric Reasoning—0
Skywork Open Reasoner 1 Technical ReportCode4
Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPOCode2
cadrille: Multi-modal CAD Reconstruction with Online Reinforcement LearningCode2
Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games—0
ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning—0
A Provable Approach for End-to-End Safe Reinforcement Learning—0
FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control—0
HDDLGym: A Tool for Studying Multi-Agent Hierarchical Problems Defined in HDDL with OpenAI GymCode0
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment GroundingCode1
Rendering-Aware Reinforcement Learning for Vector Graphics Generation—0
Reinforcing General Reasoning without VerifiersCode2
SPA-RL: Reinforcing LLM Agents via Stepwise Progress AttributionCode2
Learning optimal treatment strategies for intraoperative hypotension using deep reinforcement learning—0
R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement LearningCode1
Interactive OT Gym: A Reinforcement Learning-Based Interactive Optical tweezer (OT)-Driven Microrobotics Simulation Platform—0
Breaking the Performance Ceiling in Complex Reinforcement Learning requires Inference Strategies—0
Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RLCode1
Show:102550
← PrevPage 10 of 605Next →

Benchmark Results

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