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 376–400 of 15113 papers

TitleStatusHype
Dialogue Learning With Human-In-The-LoopCode2
Decoupling Representation Learning from Reinforcement LearningCode2
DayDreamer: World Models for Physical Robot LearningCode2
Datasets and Benchmarks for Offline Safe Reinforcement LearningCode2
D4RL: Datasets for Deep Data-Driven Reinforcement LearningCode2
Craftium: An Extensible Framework for Creating Reinforcement Learning EnvironmentsCode2
PC-Gym: Benchmark Environments For Process Control ProblemsCode2
CTR-Driven Advertising Image Generation with Multimodal Large Language ModelsCode2
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with TransformersCode2
Curiosity-driven Red-teaming for Large Language ModelsCode2
Deep Reinforcement Learning for Multi-Agent InteractionCode2
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and ExperimentationCode2
EfficientZero V2: Mastering Discrete and Continuous Control with Limited DataCode2
Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement LearningCode2
Policy improvement by planning with GumbelCode2
Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning AlgorithmsCode1
A Comprehensive Survey of Data Augmentation in Visual Reinforcement LearningCode1
Control-Informed Reinforcement Learning for Chemical ProcessesCode1
A Composable Specification Language for Reinforcement Learning TasksCode1
A Boolean Task Algebra for Reinforcement LearningCode1
Contrastive Variational Reinforcement Learning for Complex ObservationsCode1
Controlling the Risk of Conversational Search via Reinforcement LearningCode1
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLCode1
Contrastive Reinforcement Learning of Symbolic Reasoning DomainsCode1
Contrastive State Augmentations for Reinforcement Learning-Based Recommender SystemsCode1
Show:102550
← PrevPage 16 of 605Next →

Benchmark Results

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