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 2161–2170 of 15113 papers

TitleStatusHype
Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks—0
REBEL: Reinforcement Learning via Regressing Relative RewardsCode2
Offline Reinforcement Learning with Behavioral Supervisor Tuning—0
A fast balance optimization approach for charging enhancement of lithium-ion battery packs through deep reinforcement learningCode1
ActiveRIR: Active Audio-Visual Exploration for Acoustic Environment Modeling—0
DPO: A Differential and Pointwise Control Approach to Reinforcement Learning—0
GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL—0
An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models—0
Planning the path with Reinforcement Learning: Optimal Robot Motion Planning in RoboCup Small Size League EnvironmentsCode0
Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robot—0
Show:102550
← PrevPage 217 of 1512Next →

Benchmark Results

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