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 3601–3610 of 15113 papers

TitleStatusHype
User Retention-oriented Recommendation with Decision TransformerCode1
Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning—0
Provably Efficient Model-Free Algorithms for Non-stationary CMDPs—0
Optimal foraging strategies can be learnedCode0
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-TuningCode1
Evolving Populations of Diverse RL Agents with MAP-Elites—0
Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective—0
Power and Interference Control for VLC-Based UDN: A Reinforcement Learning Approach—0
Exploiting Contextual Structure to Generate Useful Auxiliary Tasks—0
Variance-aware robust reinforcement learning with linear function approximation under heavy-tailed rewards—0
Show:102550
← PrevPage 361 of 1512Next →

Benchmark Results

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