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 1431–1440 of 15113 papers

TitleStatusHype
Learning Task Informed AbstractionsCode1
Causal Reinforcement Learning using Observational and Interventional DataCode1
Multi-task curriculum learning in a complex, visual, hard-exploration domain: MinecraftCode1
Graph Convolutional Memory using Topological PriorsCode1
Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robotCode1
Compositional Reinforcement Learning from Logical SpecificationsCode1
Model-Based Reinforcement Learning via Latent-Space CollocationCode1
Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy EvaluationCode1
Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument RelationsCode1
Local policy search with Bayesian optimizationCode1
Show:102550
← PrevPage 144 of 1512Next →

Benchmark Results

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