Aayush Danagi
Bihar, India
Summary
🤩
Rockstar🎓
Top SchoolAayush Danagi is a software engineer with 10 years of experience focused on applying machine learning and engineering to finance and economic domains. Based in Bihar, India, he seeks opportunities to drive innovation and disruption in financial systems while combining practical coding skills with domain curiosity. An active contributor to open-source ML tooling, he made significant enhancements to the popular PyTorch-based reinforcement learning library Tianshou—implementing and testing Soft Actor-Critic features such as auto alpha tuning and discrete-action adaptations. His work shows a strong grasp of reinforcement learning algorithms, practical experimentation, and library-quality code. Known for blending research-minded problem solving with production-oriented implementation, he aims to translate advanced ML methods into impactful financial products.
10 years of coding experience
Kendriya Vidyalaya Sangathan
Github Skills (8)
pytorch10
sac10
python10
reinforcement-learning10
ddpg9
ppp9
test-automation7
tdd6
Programming languages (2)
Github contributions (5)
thu-ml/tianshou
Jun 2020 - Sep 2020
An elegant PyTorch deep reinforcement learning library.
Role in this project:
ML Engineer
ML EngineerContributions:35 reviews, 5 commits, 13 PRs in 3 months
Contributions summary:Aayush made significant contributions to the `tianshou` library, a deep reinforcement learning library. The commits focused on implementing and refining the Soft Actor-Critic (SAC) algorithm, including adding auto alpha tuning, exploration noise, and adapting the implementation to discrete action spaces. The user also introduced new tests for the SAC algorithm within a continuous control environment, indicating a focus on practical application and functionality. These contributions demonstrate a strong understanding of reinforcement learning techniques and library development.
deep-reinforcement-learningbenchmarknpgtd3reinforcement
danagi/tianshou
Jun 2020 - Jul 2020
An elegant, flexible, and superfast PyTorch deep Reinforcement Learning platform.
Contributions:12 PRs, 18 pushes in 16 days
pytorchsuperfastlearning-platformdeep-learningreinforcement-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.