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 71–80 of 15113 papers

TitleStatusHype
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using SparsityCode0
Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations—0
Multi-Task Lifelong Reinforcement Learning for Wireless Sensor Networks—0
From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation—0
VRAIL: Vectorized Reward-based Attribution for Interpretable Learning—0
Reinforcement Learning-Based Policy Optimisation For Heterogeneous Radio Access—0
Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks—0
Multi-Agent Reinforcement Learning for Autonomous Multi-Satellite Earth Observation: A Realistic Case Study—0
Steering Your Diffusion Policy with Latent Space Reinforcement Learning—0
PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning—0
Show:102550
← PrevPage 8 of 1512Next →

Benchmark Results

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