Finding Theta — Independent AI Research & Experimentation

Projects
Mesozoic Labs
Reinforce Tactics
Work
Experiments
Deep Dives
Contact
English
Korean
Chinese
French
Spanish

Projects ▾

Reinforce Tactics Mesozoic Labs Downforce Robotics

Work ▾

Deep Dives Experiments Publications

Featured Article

Projects

Reinforce Tactics: A Technical Compendium and Analysis of Large Language Model Performance in Stochastic Strategy Environments

Explore a technical case study on 'Reinforce Tactics,' a new RL environment where traditional game theory outperforms the latest LLMs by a massive margin, exposing critical flaws in token-based reasoning.

January 1, 2026

Read Article →

Featured Projects

Long-running research initiatives and experiments

Reinforce Tactics

Strategy game made for RL

Reinforce Tactics

A 2D strategy game built for exploring reinforcement learning strategies. Testing various RL algorithms in competitive multi-agent scenarios with complex state spaces.

Mesozoic Labs

Building robotic dinosaurs

Building robotic dinosaurs to explore biomechanics, locomotion, and control systems. Combining paleontology with modern robotics and machine learning for movement optimization.

Recent Posts

Filter by:

All

Experiments

Projects

Deep Dives

Ultimate Guide to Contextual Bandits: From Theory to Python Implementation

Discover the ultimate guide to contextual bandits, covering everything from core theory and key algorithms to a complete Python implementation with code for building powerful personalization and recommendation systems

Agentic AI: The Autonomous Evolution of Machine Learning and Its Dawn in Robotics

Explore Agentic AI, the next frontier in machine learning. Discover how autonomous agents learn, act independently, and are revolutionizing the field of robotics.

Bridging Worlds: How Visual Language Action Models are Teaching Robots to See, Understand, and Act

Understand how Visual Language Action Models (VLAs) let robots follow commands by fusing AI vision and language for action, demonstrated with a conceptual Python robotics simulation

Mastering Robotic Manipulation with Reinforcement Learning: TQC and DDPG for Fetch Environments

Using reinforcement learning (RL), specifically Truncated Quantile Critics (TQC) and Deep Deterministic Policy Gradient (DDPG), to solve the Fetch environments in Gymnasium Robotics

January 1, 2025

Mastering Atari's Pong with Reinforcement Learning: Overcoming Sparse Rewards and Optimizing Performance

Train an RL agent to master Atari's Pong with sparse rewards and high-dimensional inputs. Explore preprocessing, replay buffers, and performance-boosting strategies

October 1, 2024

Top CMS Platforms in 2023

A look at the most popular CMS platforms available in 2023.