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 3771–3780 of 15113 papers

TitleStatusHype
Combining Automated Optimisation of Hyperparameters and Reward ShapeCode0
Leveraging Reinforcement Learning in Red Teaming for Advanced Ransomware Attack Simulations—0
Human-Object Interaction from Human-Level Instructions—0
Privacy Preserving Reinforcement Learning for Population Processes—0
The State-Action-Reward-State-Action Algorithm in Spatial Prisoner's Dilemma Game—0
ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI FeedbackCode0
EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data—0
Uncertainty-Aware Reward-Free Exploration with General Function ApproximationCode0
Decentralized RL-Based Data Transmission Scheme for Energy Efficient Harvesting—0
KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement LearningCode0
Show:102550
← PrevPage 378 of 1512Next →

Benchmark Results

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