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 1826–1850 of 15113 papers

TitleStatusHype
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 74 of 605Next →

Benchmark Results

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