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 1101–1125 of 15113 papers

TitleStatusHype
Trust Region-Based Safe Distributional Reinforcement Learning for Multiple ConstraintsCode1
Zero-Shot Compositional Policy Learning via Language GroundingCode1
Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement LearningCode1
Embodied Synaptic Plasticity with Online Reinforcement learningCode1
End-to-End Affordance Learning for Robotic ManipulationCode1
A Workflow for Offline Model-Free Robotic Reinforcement LearningCode1
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning RateCode1
Avalanche RL: a Continual Reinforcement Learning LibraryCode1
Avalon: A Benchmark for RL Generalization Using Procedurally Generated WorldsCode1
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning ApproachCode1
Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and PlanningCode1
AutoPhoto: Aesthetic Photo Capture using Reinforcement LearningCode1
FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior RegularizationCode1
Efficient Meta Reinforcement Learning for Preference-based Fast AdaptationCode1
Efficient Pressure: Improving efficiency for signalized intersectionsCode1
Efficient Reinforcement Learning Through Trajectory GenerationCode1
Efficient Active Search for Combinatorial Optimization ProblemsCode1
Action Branching Architectures for Deep Reinforcement LearningCode1
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement LearningCode1
A Deep Reinforcement Learning Framework for the Financial Portfolio Management ProblemCode1
AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement LearningCode1
Efficient Continuous Control with Double Actors and Regularized CriticsCode1
BabyAI 1.1Code1
Autonomous Racing using a Hybrid Imitation-Reinforcement Learning ArchitectureCode1
Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement LearningCode1
Show:102550
← PrevPage 45 of 605Next →

Benchmark Results

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