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 3311–3320 of 15113 papers

TitleStatusHype
CQM: Curriculum Reinforcement Learning with a Quantized World Model—0
AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning—0
CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks—0
Decentralized Multi-Agent Reinforcement Learning for Task Offloading Under Uncertainty—0
Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method—0
Decentralized Multi-Robot Formation Control Using Reinforcement Learning—0
Decentralized Reinforcement Learning for Multi-Target Search and Detection by a Team of Drones—0
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions—0
C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks—0
A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning—0
Show:102550
← PrevPage 332 of 1512Next →

Benchmark Results

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