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 1426–1450 of 15113 papers

TitleStatusHype
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 58 of 605Next →

Benchmark Results

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