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 9751–9775 of 15113 papers

TitleStatusHype
Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control—0
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective—0
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited—0
Reward Machines: Exploiting Reward Function Structure in Reinforcement LearningCode1
Safety Aware Reinforcement Learning (SARL)—0
Reinforcement Learning with Random DelaysCode1
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning—0
Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model AdaptationCode1
Heterogeneous Multi-Agent Reinforcement Learning for Unknown Environment Mapping—0
Learning Diverse Options via InfoMax Termination CriticCode0
Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy GamesCode1
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement LearningCode1
Learning to Generalize for Sequential Decision MakingCode0
Goal-directed Generation of Discrete Structures with Conditional Generative Models—0
A Reinforcement Learning Approach for Rebalancing Electric Vehicle Sharing SystemsCode1
Sentiment Analysis for Reinforcement Learning—0
Meta-Learning of Structured Task Distributions in Humans and MachinesCode0
Policy Learning Using Weak SupervisionCode0
The act of remembering: a study in partially observable reinforcement learning—0
Deep Reinforcement Learning for Collaborative Edge Computing in Vehicular Networks—0
A Distributed Model-Free Ride-Sharing Approach for Joint Matching, Pricing, and Dispatching using Deep Reinforcement Learning—0
Deep Reinforcement Learning for Electric Vehicle Routing Problem with Time Windows—0
Test-Cost Sensitive Methods for Identifying Nearby Points—0
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play—0
FORK: A Forward-Looking Actor For Model-Free Reinforcement LearningCode1
Show:102550
← PrevPage 391 of 605Next →

Benchmark Results

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