Lead AI Engineer · Writing since 2016

Hi, I'm Sina. I build and train AI systems.

Lead AI Engineer. I write about reinforcement learning, transformers, multi-agent systems, and the tools I build along the way.

Explore by topic

Latest writing

Full archive →
·3 min·Deep RL with Unity 3/3

DDPG on Reacher: Twenty Arms Chasing a Balloon

DDPG completes the Unity Reacher task. Twenty robot arms use one shared replay buffer. This post shows the actor-critic setup and why the training was easier than Tennis.

·3 min·Deep RL with Unity 2/3

Two DDPG Agents Learning to Play Tennis

Two DDPG agents learn to play tennis in the Unity Tennis environment. This post shows the continuous actions, the shared sparse rewards, the methods that did not work and the settings that completed the task.

·2 min·Deep RL with Unity 1/3

Training a DQN Agent to Collect Bananas in Unity

A DQN agent learns to collect bananas in the Unity Banana Collector environment. This post shows the Q-network, the replay buffer, the target network settings and the result (+13 over 100 episodes).

·2 min·Learn SSH 3/3

Learn SSH: Config File

Use the ~/.ssh/config file to connect to servers by name, with identity files, multiple hosts, ProxyJump through a jump server, and wildcard patterns.

Read in order

Series

Multi-part guides that build on each other, start to finish.

From the archive

All 16 posts by year →

New posts, no noise.

Subscribe to the RSS feed, or follow along on GitHub, LinkedIn and the RL Factory YouTube channel.