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 926–950 of 15113 papers

TitleStatusHype
Giving Up Control: Neurons as Reinforcement Learning AgentsCode1
A Benchmark Environment for Offline Reinforcement Learning in Racing GamesCode1
Goal-Aware Cross-Entropy for Multi-Target Reinforcement LearningCode1
Constrained Update Projection Approach to Safe Policy OptimizationCode1
Goal-Guided Transformer-Enabled Reinforcement Learning for Efficient Autonomous NavigationCode1
Accelerating Exploration with Unlabeled Prior DataCode1
A Meta-Reinforcement Learning Algorithm for Causal DiscoveryCode1
Constrained Policy Optimization via Bayesian World ModelsCode1
Gradient Imitation Reinforcement Learning for Low Resource Relation ExtractionCode1
A Benchmark Environment Motivated by Industrial Control ProblemsCode1
Graph Convolutional Value Decomposition in Multi-Agent Reinforcement LearningCode1
Graph Meta-Reinforcement Learning for Transferable Autonomous Mobility-on-DemandCode1
Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand SystemsCode1
Constrained Variational Policy Optimization for Safe Reinforcement LearningCode1
Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM ReasoningCode1
Active Exploration for Inverse Reinforcement LearningCode1
GreenLight-Gym: Reinforcement learning benchmark environment for control of greenhouse production systemsCode1
Reliable Conditioning of Behavioral Cloning for Offline Reinforcement LearningCode1
Zero-Shot Reinforcement Learning from Low Quality DataCode1
Consistency Models as a Rich and Efficient Policy Class for Reinforcement LearningCode1
Guiding Online Reinforcement Learning with Action-Free Offline PretrainingCode1
Constrained episodic reinforcement learning in concave-convex and knapsack settingsCode1
Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-InteractionCode1
Continuous Deep Q-Learning with Model-based AccelerationCode1
Deep Active Inference for Partially Observable MDPsCode1
Show:102550
← PrevPage 38 of 605Next →

Benchmark Results

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