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 1376–1400 of 15113 papers

TitleStatusHype
FairStream: Fair Multimedia Streaming Benchmark for Reinforcement Learning AgentsCode0
GFlowNet Fine-tuning for Diverse Correct Solutions in Mathematical Reasoning Tasks—0
Off-Policy Selection for Initiating Human-Centric Experimental Design—0
OGBench: Benchmarking Offline Goal-Conditioned RLCode3
Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning—0
Random Policy Enables In-Context Reinforcement Learning within Trust Horizons—0
On-Robot Reinforcement Learning with Goal-Contrastive Rewards—0
Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting—0
Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces—0
Offline Reinforcement Learning with OOD State Correction and OOD Action SuppressionCode1
AgentForge: A Flexible Low-Code Platform for Reinforcement Learning Agent DesignCode0
Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors—0
Adversarial Environment Design via Regret-Guided Diffusion Models—0
PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds—0
SAMG: State-Action-Aware Offline-to-Online Reinforcement Learning with Offline Model Guidance—0
Learn 2 Rage: Experiencing The Emotional Roller Coaster That Is Reinforcement Learning—0
Optimizing Load Scheduling in Power Grids Using Reinforcement Learning and Markov Decision Processes—0
The Hive Mind is a Single Reinforcement Learning Agent—0
Primal-Dual Spectral Representation for Off-policy Evaluation—0
Leveraging Skills from Unlabeled Prior Data for Efficient Online ExplorationCode1
Dynamic Spectrum Access for Ambient Backscatter Communication-assisted D2D Systems with Quantum Reinforcement Learning—0
Process Supervision-Guided Policy Optimization for Code Generation—0
Learning Versatile Skills with Curriculum MaskingCode0
Multi-Modal Transformer and Reinforcement Learning-based Beam Management—0
Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts—0
Show:102550
← PrevPage 56 of 605Next →

Benchmark Results

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