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 3861–3870 of 15113 papers

TitleStatusHype
DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays—0
Prompt-based Visual Alignment for Zero-shot Policy Transfer—0
From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation—0
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms—0
"Give Me an Example Like This": Episodic Active Reinforcement Learning from DemonstrationsCode0
UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning—0
Smaller Batches, Bigger Gains? Investigating the Impact of Batch Sizes on Reinforcement Learning Based Real-World Production Scheduling—0
A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning—0
Rectifying Reinforcement Learning for Reward Matching—0
FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning—0
Show:102550
← PrevPage 387 of 1512Next →

Benchmark Results

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