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 1401–1450 of 15113 papers

TitleStatusHype
Co-designing Intelligent Control of Building HVACs and MicrogridsCode1
Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement LearningCode1
Megaverse: Simulating Embodied Agents at One Million Experiences per SecondCode1
Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic SystemsCode1
A Reinforcement Learning Environment for Mathematical Reasoning via Program SynthesisCode1
Surgical Instruction Generation with TransformersCode1
ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image EnhancementCode1
Shortest-Path Constrained Reinforcement Learning for Sparse Reward TasksCode1
Teaching Agents how to Map: Spatial Reasoning for Multi-Object NavigationCode1
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph DrawingCode1
Explore and Control with Adversarial SurpriseCode1
Conservative Offline Distributional Reinforcement LearningCode1
Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and ResultsCode1
Backprop-Free Reinforcement Learning with Active Neural Generative CodingCode1
BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGymCode1
Offline Meta-Reinforcement Learning with Online Self-SupervisionCode1
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal TransformersCode1
Distributed Online Service Coordination Using Deep Reinforcement LearningCode1
THE SJTU SYSTEM FOR DCASE2021 CHALLENGE TASK 6: AUDIO CAPTIONING BASED ON ENCODER PRE-TRAINING AND REINFORCEMENT LEARNINGCode1
Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement LearningCode1
AdaRL: What, Where, and How to Adapt in Transfer Reinforcement LearningCode1
Agents that Listen: High-Throughput Reinforcement Learning with Multiple Sensory SystemsCode1
Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and ExploitationCode1
Mava: a research library for distributed multi-agent reinforcement learning in JAXCode1
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement LearningCode1
Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic RewardsCode1
Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-EnsembleCode1
Distilling Reinforcement Learning Tricks for Video GamesCode1
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data AugmentationCode1
Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros StudyCode1
Learning Task Informed AbstractionsCode1
Multi-task curriculum learning in a complex, visual, hard-exploration domain: MinecraftCode1
Causal Reinforcement Learning using Observational and Interventional DataCode1
Graph Convolutional Memory using Topological PriorsCode1
Compositional Reinforcement Learning from Logical SpecificationsCode1
Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robotCode1
Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy EvaluationCode1
Model-Based Reinforcement Learning via Latent-Space CollocationCode1
Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument RelationsCode1
Local policy search with Bayesian optimizationCode1
OptiDICE: Offline Policy Optimization via Stationary Distribution Correction EstimationCode1
Distributed Heuristic Multi-Agent Path Finding with CommunicationCode1
A Max-Min Entropy Framework for Reinforcement LearningCode1
Towards Safe Reinforcement Learning via Constraining Conditional Value at RiskCode1
MADE: Exploration via Maximizing Deviation from Explored RegionsCode1
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual PoliciesCode1
Contrastive Reinforcement Learning of Symbolic Reasoning DomainsCode1
Safe Reinforcement Learning Using Advantage-Based InterventionCode1
Revisiting the Weaknesses of Reinforcement Learning for Neural Machine TranslationCode1
Solving Continuous Control with Episodic MemoryCode1
Show:102550
← PrevPage 29 of 303Next →

Benchmark Results

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