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 476–500 of 15113 papers

TitleStatusHype
Remote Rowhammer Attack using Adversarial Observations on Federated Learning Clients—0
Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning—0
Active Perception for Tactile Sensing: A Task-Agnostic Attention-Based Approach—0
Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs—0
On Corruption-Robustness in Performative Reinforcement Learning—0
RL-DAUNCE: Reinforcement Learning-Driven Data Assimilation with Uncertainty-Aware Constrained Ensembles—0
Taming OOD Actions for Offline Reinforcement Learning: An Advantage-Based Approach—0
USPR: Learning a Unified Solver for Profiled RoutingCode0
Flow-GRPO: Training Flow Matching Models via Online RLCode7
Enhancing Reinforcement Learning for the Floorplanning of Analog ICs with Beam Search—0
Multi-agent Embodied AI: Advances and Future Directions—0
Large Language Models are Autonomous Cyber DefendersCode0
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers—0
ZeroSearch: Incentivize the Search Capability of LLMs without SearchingCode5
Extending a Quantum Reinforcement Learning Exploration Policy with Flags to Connect Four—0
Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization—0
Risk-sensitive Reinforcement Learning Based on Convex Scoring Functions—0
Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems—0
Deep Q-Network (DQN) multi-agent reinforcement learning (MARL) for Stock Trading—0
VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making—0
AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control—0
Actor-Critics Can Achieve Optimal Sample Efficiency—0
The Steganographic Potentials of Language Models—0
Online Phase Estimation of Human Oscillatory Motions using Deep Learning—0
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement LearningCode3
Show:102550
← PrevPage 20 of 605Next →

Benchmark Results

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