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 1851–1900 of 15113 papers

TitleStatusHype
Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsCode1
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience ReplayCode1
Long-Term Planning with Deep Reinforcement Learning on Autonomous DronesCode1
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter OptimizationCode1
One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic ControlCode1
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement LearningCode1
Provably Safe PAC-MDP Exploration Using AnalogiesCode1
LFQ: Online Learning of Per-flow Queuing Policies using Deep Reinforcement LearningCode1
Meta-Learning through Hebbian Plasticity in Random NetworksCode1
Enhancing SAT solvers with glue variable predictionsCode1
Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement LearningCode1
Counterfactual Data Augmentation using Locally Factored DynamicsCode1
Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement LearningCode1
Bidirectional Model-based Policy OptimizationCode1
Reward Machines for Cooperative Multi-Agent Reinforcement LearningCode1
Verifiably Safe Exploration for End-to-End Reinforcement LearningCode1
Debiased Contrastive LearningCode1
Reinforcement Learning based Control of Imitative Policies for Near-Accident DrivingCode1
UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning ApproachCode1
MDP Homomorphic Networks: Group Symmetries in Reinforcement LearningCode1
Evaluating the Performance of Reinforcement Learning AlgorithmsCode1
Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEsCode1
Image Classification by Reinforcement Learning with Two-State Q-LearningCode1
A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity RewardsCode1
Online 3D Bin Packing with Constrained Deep Reinforcement LearningCode1
Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data AugmentationCode1
Intrinsic Reward Driven Imitation Learning via Generative ModelCode1
What can I do here? A Theory of Affordances in Reinforcement LearningCode1
Critic Regularized RegressionCode1
DISK: Learning local features with policy gradientCode1
The NetHack Learning EnvironmentCode1
Expert-Supervised Reinforcement Learning for Offline Policy Learning and EvaluationCode1
Automatic Data Augmentation for Generalization in Deep Reinforcement LearningCode1
Experience Replay with Likelihood-free Importance WeightsCode1
Adversarial Soft Advantage Fitting: Imitation Learning without Policy OptimizationCode1
Safe Reinforcement Learning via Curriculum InductionCode1
Learning with AMIGo: Adversarially Motivated Intrinsic GoalsCode1
Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic EnvironmentsCode1
Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement LearningCode1
Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement LearningCode1
Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian ProcessesCode1
Deep Implicit Coordination Graphs for Multi-agent Reinforcement LearningCode1
DREAM: Deep Regret minimization with Advantage baselines and Model-free learningCode1
Learning Invariant Representations for Reinforcement Learning without ReconstructionCode1
Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement LearningCode1
Converting Biomechanical Models from OpenSim to MuJoCoCode1
Automatic Curriculum Learning through Value DisagreementCode1
Forgetful Experience Replay in Hierarchical Reinforcement Learning from DemonstrationsCode1
Neural Ordinary Differential Equation Control of Dynamics on GraphsCode1
Learning to Track Dynamic Targets in Partially Known EnvironmentsCode1
Show:102550
← PrevPage 38 of 303Next →

Benchmark Results

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