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 2311–2320 of 15113 papers

TitleStatusHype
Multi-Objective Optimization Using Adaptive Distributed Reinforcement Learning—0
Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis—0
Meta-operators for Enabling Parallel Planning Using Deep Reinforcement Learning—0
Learning to Describe for Predicting Zero-shot Drug-Drug InteractionsCode0
LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban EnvironmentsCode2
HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback—0
TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement LearningCode0
Adaptive Gain Scheduling using Reinforcement Learning for Quadcopter ControlCode0
A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware PerspectiveCode0
ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment—0
Show:102550
← PrevPage 232 of 1512Next →

Benchmark Results

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