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 1951–1975 of 15113 papers

TitleStatusHype
Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RLCode1
ALLSTEPS: Curriculum-driven Learning of Stepping Stone SkillsCode1
Learning hierarchical behavior and motion planning for autonomous drivingCode1
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document SummarizationCode1
Curious Hierarchical Actor-Critic Reinforcement LearningCode1
Plan2Vec: Unsupervised Representation Learning by Latent PlansCode1
CARL: Controllable Agent with Reinforcement Learning for Quadruped LocomotionCode1
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open ProblemsCode1
Off-Policy Adversarial Inverse Reinforcement LearningCode1
Learning Collaborative Agents with Rule Guidance for Knowledge Graph ReasoningCode1
Logic and the 2-Simplicial TransformerCode1
RaCT: Toward Amortized Ranking-Critical Training For Collaborative FilteringCode1
Implementation Matters in Deep RL: A Case Study on PPO and TRPOCode1
Option Discovery using Deep Skill ChainingCode1
Deep Symbolic Superoptimization Without Human KnowledgeCode1
Reinforcement Learning with Augmented DataCode1
Hierarchical Reinforcement Learning for Automatic Disease DiagnosisCode1
Actor-Critic Reinforcement Learning for Control with Stability GuaranteeCode1
Transferable Active Grasping and Real Embodied DatasetCode1
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from PixelsCode1
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement LearningCode1
First return, then exploreCode1
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement LearningCode1
CFR-RL: Traffic Engineering with Reinforcement Learning in SDNCode1
Self-Paced Deep Reinforcement LearningCode1
Show:102550
← PrevPage 79 of 605Next →

Benchmark Results

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