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 3001–3010 of 15113 papers

TitleStatusHype
Efficient Reinforcement Learning for Jumping MonopodsCode0
Investigating the Impact of Action Representations in Policy Gradient Algorithms—0
Safe Reinforcement Learning with Dual Robustness—0
Reasoning with Latent Diffusion in Offline Reinforcement LearningCode1
Improved Monte Carlo tree search formulation with multiple root nodes for discrete sizing optimization of truss structures—0
Risk-Aware Reinforcement Learning through Optimal Transport Theory—0
Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement LearningCode1
Representation Learning in Low-rank Slate-based Recommender Systems—0
Signal Temporal Logic Neural Predictive Control—0
Verifiable Reinforcement Learning Systems via Compositionality—0
Show:102550
← PrevPage 301 of 1512Next →

Benchmark Results

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