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 31–40 of 15113 papers

TitleStatusHype
Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation—0
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning—0
2048: Reinforcement Learning in a Delayed Reward Environment—0
Kwai Keye-VL Technical ReportCode4
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across DomainsCode0
Constructing Non-Markovian Decision Process via History AggregatorCode0
RAG-R1 : Incentivize the Search and Reasoning Capabilities of LLMs through Multi-query ParallelismCode5
Listener-Rewarded Thinking in VLMs for Image Preferences—0
A Survey of Continual Reinforcement Learning—0
Advancements and Challenges in Continual Reinforcement Learning: A Comprehensive Review—0
Show:102550
← PrevPage 4 of 1512Next →

Benchmark Results

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