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 241–250 of 15113 papers

TitleStatusHype
iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvementCode2
Craftium: An Extensible Framework for Creating Reinforcement Learning EnvironmentsCode2
Efficient World Models with Context-Aware TokenizationCode2
GenRL: Multimodal-foundation world models for generalization in embodied agentsCode2
Direct Multi-Turn Preference Optimization for Language AgentsCode2
MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency TradingCode2
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy OptimizationCode2
Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous controlCode2
Diffusion Actor-Critic with Entropy RegulatorCode2
AGILE: A Novel Reinforcement Learning Framework of LLM AgentsCode2
Show:102550
← PrevPage 25 of 1512Next →

Benchmark Results

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