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 951–960 of 15113 papers

TitleStatusHype
Enhancing Pre-Trained Decision Transformers with Prompt-Tuning Bandits—0
Towards Smarter Sensing: 2D Clutter Mitigation in RL-Driven Cognitive MIMO Radar—0
Convergent NMPC-based Reinforcement Learning Using Deep Expected Sarsa and Nonlinear Temporal Difference Learning—0
Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits—0
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM GuardrailsCode1
Mirror Descent Actor Critic via Bounded Advantage Learning—0
Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning—0
LLM Alignment as Retriever Optimization: An Information Retrieval Perspective—0
Illuminating Spaces: Deep Reinforcement Learning and Laser-Wall Partitioning for Architectural Layout Generation—0
Training Language Models to Reason EfficientlyCode2
Show:102550
← PrevPage 96 of 1512Next →

Benchmark Results

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