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 1801–1850 of 15113 papers

TitleStatusHype
Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning—0
Structural Design Through Reinforcement LearningCode0
Learning In-Hand Translation Using Tactile Skin With Shear and Normal Force Sensing—0
Continuous Control with Coarse-to-fine Reinforcement Learning—0
Preference-Guided Reinforcement Learning for Efficient ExplorationCode0
Can Learned Optimization Make Reinforcement Learning Less Difficult?Code1
Intercepting Unauthorized Aerial Robots in Controlled Airspace Using Reinforcement Learning—0
An open source Multi-Agent Deep Reinforcement Learning Routing Simulator for satellite networks—0
Periodic agent-state based Q-learning for POMDPs—0
On Bellman equations for continuous-time policy evaluation I: discretization and approximation—0
iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvementCode2
Multi-agent Reinforcement Learning-based Network Intrusion Detection System—0
Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot NavigationCode1
Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments—0
FOSP: Fine-tuning Offline Safe Policy through World Models—0
Simplifying Deep Temporal Difference LearningCode3
Using Petri Nets as an Integrated Constraint Mechanism for Reinforcement Learning Tasks—0
Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based ShieldingCode0
Robust Decision Transformer: Tackling Data Corruption in Offline RL via Sequence Modeling—0
Hindsight Preference Learning for Offline Preference-based Reinforcement LearningCode1
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents—0
Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language ModelsCode0
Craftium: An Extensible Framework for Creating Reinforcement Learning EnvironmentsCode2
ROER: Regularized Optimal Experience ReplayCode0
RobocupGym: A challenging continuous control benchmark in RobocupCode1
Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes—0
Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement LearningCode0
PWM: Policy Learning with Multi-Task World Models—0
To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement Learning—0
Reinforcement Learning-driven Data-intensive Workflow Scheduling for Volunteer Edge-Cloud—0
Safe Reinforcement Learning for Power System Control: A Review—0
DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without ReconstructionCode0
Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators—0
Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning—0
Digital Twin-Assisted Data-Driven Optimization for Reliable Edge Caching in Wireless Networks—0
A Review of Safe Reinforcement Learning Methods for Modern Power Systems—0
Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes—0
PUZZLES: A Benchmark for Neural Algorithmic ReasoningCode1
External Model Motivated Agents: Reinforcement Learning for Enhanced Environment SamplingCode0
Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning—0
Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems—0
Decision Transformer for IRS-Assisted Systems with Diffusion-Driven Generative Channels—0
Fuzzy Logic Guided Reward Function Variation: An Oracle for Testing Reinforcement Learning ProgramsCode0
Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs—0
Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control PriorsCode0
Operator World Models for Reinforcement LearningCode0
Multi-agent Cooperative Games Using Belief Map Assisted TrainingCode0
Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning—0
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion—0
Efficient World Models with Context-Aware TokenizationCode2
Show:102550
← PrevPage 37 of 303Next →

Benchmark Results

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