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 2911–2920 of 15113 papers

TitleStatusHype
Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions—0
Multimodal Dreaming: A Global Workspace Approach to World Model-Based Reinforcement Learning—0
Subtask-Aware Visual Reward Learning from Segmented Demonstrations—0
Adaptive Reinforcement Learning for State Avoidance in Discrete Event Systems—0
Hierarchical and Modular Network on Non-prehensile Manipulation in General Environments—0
Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning—0
AutoBS: Autonomous Base Station Deployment with Reinforcement Learning and Digital Network TwinsCode0
Accelerating Model-Based Reinforcement Learning with State-Space World Models—0
R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning—0
Improving the Efficiency of a Deep Reinforcement Learning-Based Power Management System for HPC Clusters Using Curriculum Learning—0
Show:102550
← PrevPage 292 of 1512Next →

Benchmark Results

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