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 8351–8375 of 15113 papers

TitleStatusHype
Network Defense is Not a Game—0
Prospective Artificial Intelligence Approaches for Active Cyber Defence—0
Visual Navigation with Spatial AttentionCode1
GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model—0
Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting—0
Deep Reinforcement Learning in a Monetary Model—0
Singular Perturbation-based Reinforcement Learning of Two-Point Boundary Optimal Control Systems—0
Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior—0
Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls—0
Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement LearningCode0
Agent-Centric Representations for Multi-Agent Reinforcement Learning—0
Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense—0
Approximated Multi-Agent Fitted Q Iteration—0
Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement LearningCode1
Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning—0
Reinforcement learning based process optimization and strategy development in conventional tunnelingCode0
Action Advising with Advice Imitation in Deep Reinforcement LearningCode0
Learning on a Budget via Teacher ImitationCode0
Language Models are Few-Shot ButlersCode1
Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions—0
Towards Standardising Reinforcement Learning Approaches for Production Scheduling ProblemsCode1
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale—0
Predictor-Corrector(PC) Temporal Difference(TD) Learning (PCTD)—0
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills—0
An L^2 Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation—0
Show:102550
← PrevPage 335 of 605Next →

Benchmark Results

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