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 2141–2150 of 15113 papers

TitleStatusHype
Tabular and Deep Reinforcement Learning for Gittins Index—0
FLAME: Factuality-Aware Alignment for Large Language Models—0
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks—0
Learning Force Control for Legged Manipulation—0
Queue-based Eco-Driving at Roundabouts with Reinforcement Learning—0
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPOCode1
Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning—0
Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning—0
Towards Generalist Robot Learning from Internet Video: A Survey—0
Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement LearningCode0
Show:102550
← PrevPage 215 of 1512Next →

Benchmark Results

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