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 10276–10300 of 15113 papers

TitleStatusHype
NQMIX: Non-monotonic Value Function Factorization for Deep Multi-Agent Reinforcement Learning—0
Nonparametric Bayesian Inverse Reinforcement Learning for Multiple Reward Functions—0
Nonparametric Bayesian Policy Priors for Reinforcement Learning—0
Nonparametric Bellman Mappings for Reinforcement Learning: Application to Robust Adaptive Filtering—0
Nonparametric General Reinforcement Learning—0
Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration—0
Non-Robust Feature Mapping in Deep Reinforcement Learning—0
Non-stationary Reinforcement Learning under General Function Approximation—0
Nonstationary Reinforcement Learning with Linear Function Approximation—0
Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach—0
Non-stationary Risk-sensitive Reinforcement Learning: Near-optimal Dynamic Regret, Adaptive Detection, and Separation Design—0
Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning—0
No-Press Diplomacy: Modeling Multi-Agent Gameplay—0
No-Regret Exploration in Goal-Oriented Reinforcement Learning—0
No-regret Exploration in Shuffle Private Reinforcement Learning—0
No-Regret Reinforcement Learning in Smooth MDPs—0
No-Regret Reinforcement Learning with Heavy-Tailed Rewards—0
Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning—0
Normality-Guided Distributional Reinforcement Learning for Continuous Control—0
NoRML: No-Reward Meta Learning—0
Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning—0
NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds—0
Novel Reinforcement Learning Algorithm for Suppressing Synchronization in Closed Loop Deep Brain Stimulators—0
Novel Sensor Scheduling Scheme for Intruder Tracking in Energy Efficient Sensor Networks—0
NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty—0
Show:102550
← PrevPage 412 of 605Next →

Benchmark Results

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