Strategic Learning
Through Action.
An experimental reinforcement learning system exploring how strategic capability emerges from self-play, deep search loops, and state-space representation.
Parallel Monte Carlo Tree Search evaluating candidate action branches with neural priors.
Outperforming traditional evaluation heuristics via self-play representation learning.
Rapid value function stabilization using asynchronous gradient updates.
How Praxis Learns
SEARCH DYNAMICS & REINFORCEMENT
Monte Carlo Tree Search with Neural Priors
Praxis combines neural policy priors with parallel tree exploration. Rather than relying entirely on immediate feed-forward output, the agent explores tens of thousands of future board trajectories before selecting an optimal action.
Autonomous Self-Play Reinforcement Loops
The agent generates its own training data by playing millions of games against previous iterations of itself. Win/loss outcomes iteratively adjust policy weights, continually identifying weaknesses and developing counter-strategies.
Dual-Head Policy & Value Networks
A shared convolutional and transformer backbone extracts game state representations, splitting into two distinct heads: a Policy Head predicting the move distribution and a Value Head predicting expected game outcome (-1 to +1).
Read the Praxis Research Log
Explore published findings, training trajectories, and benchmark evaluations on strategic agent learning.