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 201–210 of 15113 papers

TitleStatusHype
Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control—0
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RLCode2
Towards Effective Code-Integrated ReasoningCode1
Contextual Integrity in LLMs via Reasoning and Reinforcement Learning—0
Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning—0
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning—0
Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation—0
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning EngineeringCode2
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language ModelsCode1
Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners—0
Show:102550
← PrevPage 21 of 1512Next →

Benchmark Results

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