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 701–710 of 15113 papers

TitleStatusHype
Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking—0
NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic ScenariosCode1
Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning—0
AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models—0
Mining-Gym: A Configurable RL Benchmarking Environment for Truck Dispatch SchedulingCode0
Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer LearningCode0
Evolutionary Policy Optimization—0
MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the MetaverseCode3
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-TrainingCode1
RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generation—0
Show:102550
← PrevPage 71 of 1512Next →

Benchmark Results

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