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 2061–2070 of 15113 papers

TitleStatusHype
AGILE: A Novel Reinforcement Learning Framework of LLM AgentsCode2
Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence—0
A finite time analysis of distributed Q-learning—0
Multi-turn Reinforcement Learning from Preference Human FeedbackCode1
Variational Delayed Policy OptimizationCode0
Autonomous Algorithm for Training Autonomous Vehicles with Minimal Human Intervention—0
Learning to sample fibers for goodness-of-fit testing—0
Leader Reward for POMO-Based Neural Combinatorial Optimization—0
Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systemsCode0
Maximum Entropy Reinforcement Learning via Energy-Based Normalizing FlowCode1
Show:102550
← PrevPage 207 of 1512Next →

Benchmark Results

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