Manajev AI Labs

About Me

Hey, I'm Dmitri—founder of Cryptoapps (2018-2024), now focused on Manajev AI Labs in Zurich, Switzerland. I've shifted from crafting secure crypto applications to developing reinforcement learning models and autonomous systems that drive real impact.

Specializing in RL algorithms, AI prototypes, and robotic controls that integrate easily into production—pairing reliable software skills with intelligent AI methods.

Passionate about building AI agents that learn, adapt, and scale for business challenges. Open to collaborations, consulting gigs, or targeted discussions on RL and embodied AI.

Core Expertise

• Reinforcement Learning (MAPPO, MADDPG, PPO, TD3, SAC)
• Multi-Agent Systems (Cooperative & Competitive RL)
• AI/ML (PyTorch, JAX, TensorFlow, Unity ML-Agents)
• Robotics (ROS/ROS2, C++, Simulation, Continuous Control)
• Full-Stack Dev (Python, C++, JavaScript, Secure Backends)
• Prototyping & Deployment (Docker, Cloud, Edge Computing)

Featured Projects

• RL-Odyssey Research framework for continuous control implementing DDPG, TD3, SAC, PPO, TRPO, A2C, A3C, and PG with interactive notebooks and clean experiment scripts.
• Unity Multi-Agent RL Framework Multi-agent reinforcement learning framework implementing MAPPO, MASAC, MATD3, and MADDPG with comprehensive evaluation tools.
• MADDPG Zoo (PyTorch) Modern implementation of MADDPG algorithms using PyTorch and PettingZoo environments for multi-agent RL research.
• MARL PPO Suite Clean implementations of PPO-based algorithms (MAPPO, HAPPO) for cooperative multi-agent RL in SMAC environments.
• Unity Deep RL (DDPG/TD3/SAC) State-of-the-art deep RL algorithms for continuous control tasks in Unity ML-Agents environments.
• Cryptoapps Secure cryptocurrency wallet technology and blockchain applications.

Full code on GitHub. Fork away.

Get in Touch

Email: dmitri@manajev.com

GitHub: @legalaspro

LinkedIn: @dmitri-manajev

Based in Zurich/Tallinn. Worldwide remote.