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 4191–4200 of 15113 papers

TitleStatusHype
Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble—0
Adaptive Risk-Aware Bidding with Budget Constraint in Display AdvertisingCode0
First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation—0
Few-Shot Preference Learning for Human-in-the-Loop RL—0
Understanding Self-Predictive Learning for Reinforcement Learning—0
Reinforcement Learning for UAV control with Policy and Reward Shaping—0
Reinforcement Learning for Molecular Dynamics Optimization: A Stochastic Pontryagin Maximum Principle ApproachCode0
Safe Inverse Reinforcement Learning via Control Barrier Function—0
Scalable Planning and Learning Framework Development for Swarm-to-Swarm Engagement Problems—0
Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement LearningCode0
Show:102550
← PrevPage 420 of 1512Next →

Benchmark Results

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