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 2661–2670 of 15113 papers

TitleStatusHype
Learning Polynomial Representations of Physical Objects with Application to Certifying Correct Packing Configurations—0
Reward Certification for Policy Smoothed Reinforcement LearningCode0
Spreeze: High-Throughput Parallel Reinforcement Learning Framework—0
Partial End-to-end Reinforcement Learning for Robustness Against Modelling Error in Autonomous Racing—0
KnowGPT: Knowledge Graph based Prompting for Large Language Models—0
Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and RegularizationCode0
The Generalization Gap in Offline Reinforcement LearningCode1
Modifying RL Policies with Imagined Actions: How Predictable Policies Can Enable Users to Perform Novel Tasks—0
On the calibration of compartmental epidemiological modelsCode0
Evolving Reservoirs for Meta Reinforcement LearningCode2
Show:102550
← PrevPage 267 of 1512Next →

Benchmark Results

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