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 3211–3220 of 15113 papers

TitleStatusHype
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation—0
Skill-Enhanced Reinforcement Learning Acceleration from Demonstrations—0
Reinforcement Learning for a Discrete-Time Linear-Quadratic Control Problem with an Application—0
Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study—0
AI Planning: A Primer and Survey (Preliminary Report)—0
RLZero: Direct Policy Inference from Language Without In-Domain Supervision—0
Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories—0
Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting—0
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy—0
Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning—0
Show:102550
← PrevPage 322 of 1512Next →

Benchmark Results

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