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 181–190 of 15113 papers

TitleStatusHype
Incentivizing Reasoning for Advanced Instruction-Following of Large Language ModelsCode1
KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning—0
Data-assimilated model-informed reinforcement learning—0
Trajectory First: A Curriculum for Discovering Diverse Policies—0
Reasoning-Table: Exploring Reinforcement Learning for Table ReasoningCode2
A Reinforcement Learning Approach for RIS-aided Fair Communications—0
DriveMind: A Dual-VLM based Reinforcement Learning Framework for Autonomous Driving—0
ARIA: Training Language Agents with Intention-Driven Reward Aggregation—0
MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning—0
Reinforcement Learning for Hanabi—0
Show:102550
← PrevPage 19 of 1512Next →

Benchmark Results

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