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 251–300 of 15113 papers

TitleStatusHype
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and MemoryCode2
REBEL: Reinforcement Learning via Regressing Relative RewardsCode2
FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex ManipulationCode2
G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement LearningCode2
FlowReasoner: Reinforcing Query-Level Meta-AgentsCode2
Foundation Policies with Hilbert RepresentationsCode2
Generalized Inner Loop Meta-LearningCode2
Godot Reinforcement Learning AgentsCode2
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement LearningCode2
Learning Accurate Long-term Dynamics for Model-based Reinforcement LearningCode2
FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative FinanceCode2
Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein DesignCode2
FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource AllocationCode2
Feedback Efficient Online Fine-Tuning of Diffusion ModelsCode2
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1Code2
Exploring the Limit of Outcome Reward for Learning Mathematical ReasoningCode2
Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based MethodsCode2
Flightmare: A Flexible Quadrotor SimulatorCode2
EV2Gym: A Flexible V2G Simulator for EV Smart Charging Research and BenchmarkingCode2
Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path PlanningCode2
Evolving Reservoirs for Meta Reinforcement LearningCode2
Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy OptimizationCode2
Emergent Tool Use From Multi-Agent AutocurriculaCode2
AMP: Adversarial Motion Priors for Stylized Physics-Based Character ControlCode2
EfficientZero V2: Mastering Discrete and Continuous Control with Limited DataCode2
Efficient Online Reinforcement Learning with Offline DataCode2
ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement LearningCode2
EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender SystemsCode2
AndroidEnv: A Reinforcement Learning Platform for AndroidCode2
Distributional Soft Actor-Critic with Three RefinementsCode2
Easy-to-Hard Generalization: Scalable Alignment Beyond Human SupervisionCode2
Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement LearningCode2
Flow: A Modular Learning Framework for Mixed Autonomy TrafficCode2
Direct Multi-Turn Preference Optimization for Language AgentsCode2
AGILE: A Novel Reinforcement Learning Framework of LLM AgentsCode2
DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical DialogueCode2
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement LearningCode2
Diffusion Models for Reinforcement Learning: A SurveyCode2
Accelerated Methods for Deep Reinforcement LearningCode2
DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented GenerationCode2
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with TransformersCode2
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline DataCode2
Efficient World Models with Context-Aware TokenizationCode2
A Critical Evaluation of AI Feedback for Aligning Large Language ModelsCode2
Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem SolvingCode2
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy OptimizationCode2
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function OptimizationCode2
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language ModelsCode2
Digi-Q: Learning Q-Value Functions for Training Device-Control AgentsCode2
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and ExperimentationCode2
Show:102550
← PrevPage 6 of 303Next →

Benchmark Results

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