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 2881–2890 of 15113 papers

TitleStatusHype
Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy ApproachCode0
Virtual Augmented Reality for Atari Reinforcement LearningCode0
A Lightweight Calibrated Simulation Enabling Efficient Offline Learning for Optimal Control of Real BuildingsCode0
Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration BiasCode1
Online RL in Linearly q^π-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore—0
Off-Policy Evaluation for Human Feedback—0
Reinforcement Learning-based Knowledge Graph Reasoning for Explainable Fact-checking—0
Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization—0
Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning—0
Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning—0
Show:102550
← PrevPage 289 of 1512Next →

Benchmark Results

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