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 10226–10250 of 15113 papers

TitleStatusHype
Neural Topic Model with Reinforcement Learning—0
Neural-to-Tree Policy Distillation with Policy Improvement Criterion—0
Neural Trust Region/Proximal Policy Optimization Attains Globally Optimal Policy—0
NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment—0
NeurIPS 2022 Competition: Driving SMARTS—0
NeuRL: Closed-form Inverse Reinforcement Learning for Neural Decoding—0
Neuroevolution-Based Inverse Reinforcement Learning—0
Neuromechanics-based Deep Reinforcement Learning of Neurostimulation Control in FES cycling—0
Neuromuscular Reinforcement Learning to Actuate Human Limbs through FES—0
Neuron Activation Analysis for Multi-Joint Robot Reinforcement Learning—0
Neuron as an Agent—0
Neuroprospecting with DeepRL agents—0
Neuro-Symbolic Hierarchical Rule Induction—0
Neuro-symbolic Meta Reinforcement Learning for Trading—0
Neurosymbolic Reinforcement Learning and Planning: A Survey—0
Neuro-Symbolic Reinforcement Learning with First-Order Logic—0
Neuro-Symbolic World Models for Adapting to Open World Novelty—0
NeuSaver: Neural Adaptive Power Consumption Optimization for Mobile Video Streaming—0
Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions—0
New Auction Algorithms for Path Planning, Network Transport, and Reinforcement Learning—0
New Challenges in Reinforcement Learning: A Survey of Security and Privacy—0
New Reinforcement Learning Using a Chaotic Neural Network for Emergence of "Thinking" - "Exploration" Grows into "Thinking" through Learning -—0
News-based trading strategies—0
Next-Future: Sample-Efficient Policy Learning for Robotic-Arm Tasks—0
N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs—0
Show:102550
← PrevPage 410 of 605Next →

Benchmark Results

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