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 4221–4230 of 15113 papers

TitleStatusHype
Accelerating Interactive Human-like Manipulation Learning with GPU-based Simulation and High-quality Demonstrations—0
Automata Learning meets ShieldingCode0
Online Shielding for Reinforcement Learning—0
Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance—0
RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement LearningCode1
Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward—0
DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning—0
Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics—0
MeshDQN: A Deep Reinforcement Learning Framework for Improving Meshes in Computational Fluid DynamicsCode1
STL-Based Synthesis of Feedback Controllers Using Reinforcement LearningCode0
Show:102550
← PrevPage 423 of 1512Next →

Benchmark Results

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