Reading & Tools

A curated set of papers, tools, and learning resources that inform my work across reinforcement learning, ML systems, automation, and security-aware engineering. This list will evolve as my work deepens.

Selected Papers & Notes

References that shape how I reason about systems, safety, and reliability.

Reinforcement Learning & Multi-Agent Systems

• Schulman et al. (2017) — Proximal Policy Optimization Algorithms

  arxiv.org/abs/1707.06347
• Yu et al. (2022) — The Surprising Effectiveness of MAPPO in Cooperative Multi-Agent Games

  arxiv.org/abs/2103.01955

Machine Learning Systems

• Sculley et al. (2015) — Hidden Technical Debt in Machine Learning Systems

  papers.nips.cc/.../86df7dcf

Security Foundations

• Kocher et al. (1999) — Differential Power Analysis

  iacr.org/archive/crypto99/1666/16660036.pdf

Tools & Frameworks

Practical stacks I lean on for experiments, automation, and security-aware builds.

ML / RL

• PyTorch — pytorch.org
• Stable-Baselines3 — stable-baselines3.readthedocs.io
• Weights & Biases (experiment tracking) — wandb.ai

Simulation & Robotics

• PyBullet — pybullet.org
• OpenAI Gym / Gymnasium — gymnasium.farama.org

Automation & Engineering

• Python (argparse, logging, pathlib) — docs.python.org/3
• Makefiles & simple shell scripting — gnu.org/software/make/manual/
• Git — git-scm.com/doc

Security & Analysis

• ChipWhisperer (learning reference) — chipwhisperer.readthedocs.io
• OpenSSL documentation — openssl.org/docs/

Courses & Guides

Hands-on material I use to tighten fundamentals and ship responsibly.

• Deep Reinforcement Learning (Berkeley CS285) — rail.eecs.berkeley.edu/deeprlcourse/
• Spinning Up in Deep RL (OpenAI) — spinningup.openai.com
• Learn2Cloud (cloud fundamentals) — learn2cloud.com
• OWASP Top 10 — owasp.org/www-project-top-ten/