6-max NLHE poker bot on Deep CFR. MCCFR-trained, pure-NumPy runtime, 2s/768MB sandbox. 12th of 500+, 15th of 64 in the final, Fullhouse Hackathon 2026 (Quadrature Capital).
-
Updated
Aug 5, 2026 - Python
#
deep-cfr
Here are 11 public repositories matching this topic...
High-throughput reinforcement-learning search and sampling in Rust, with caller-owned Python networks and training
python rust machine-learning reinforcement-learning dqn mcts monte-carlo-tree-search game-ai gymnasium cfr ppo alphazero self-play pettingzoo deep-cfr
-
Updated
Sep 24, 2026 - Rust
Heads-up no-limit Texas Hold'em research stack with exact Python/C++ engines, Deep CFR training, evaluation, search, and a desktop GUI.
python reinforcement-learning poker cpp pytorch game-theory texas-holdem imperfect-information-games counterfactual-regret-minimization poker-ai deep-cfr heads-up-poker
-
Updated
Aug 28, 2026 - Jupyter Notebook
Research prototype for 6-max poker AI systems using Rust, Deep-CFR-style training, PyTorch, ONNX, and controlled simulator evaluation.
rust reinforcement-learning simulation pytorch game-theory onnx imperfect-information-games counterfactual-regret-minimization research-prototype poker-ai deep-cfr no-limit-holdem
-
Updated
Nov 4, 2026 - Python
Implementation of AI Poker HULH with Deep CFR and MCCFR ES as thesis for Bachelor of Engineering degree
-
Updated
Feb 19, 2022 - TeX
Open-source GTO poker solver with neural network strategy approximation and 75ms real-time search decisions. Built for study, research, and extension.AI built in five stages: CFR, card abstraction, Deep CFR, and real-time search. Readable code, full docs, 27 tests.
-
Updated
Jul 1, 2026 - Python
A 6-max No-Limit Texas Hold'em AI lab: full poker engine, five paradigms (rule-based, Monte Carlo, tabular CFR, Deep CFR, Q-learning), reproducible training pipelines, a 100k-hand benchmark, and a 28-page paper on the math behind them.
machine-learning reinforcement-learning poker monte-carlo q-learning game-theory texas-holdem cfr counterfactual-regret-minimization deep-cfr
-
Updated
Sep 15, 2026 - TypeScript
Deep CFR, offline RL (CQL/IQL) and self-play evaluation for 6-max No-Limit Hold'em in PyTorch
reinforcement-learning pytorch multi-agent game-theory game-ai texas-holdem imperfect-information-games self-play counterfactual-regret-minimization offline-reinforcement-learning poker-ai deep-cfr no-limit-holdem
-
Updated
Nov 2, 2026 - Python
Game-theory and RL agents measured against exact optima: CFR+, Deep CFR and DQN across six games, with a live in-browser console.
reinforcement-learning poker pytorch dqn game-theory nash-equilibrium cfr counterfactual-regret-minimization deep-cfr
-
Updated
Sep 29, 2026 - Python
B.Sc. Mathematics Thesis: Theoretical & empirical variance reduction analysis in Deep Counterfactual Regret Minimization (OpenSpiel).
reinforcement-learning game-theory bachelor-thesis variance-reduction counterfactual-regret-minimization openspiel deep-cfr
-
Updated
Oct 26, 2026
Game-theory solver for heads-up pot-limit Drawmaha, built as a validation ladder: regret matching → CFR on Kuhn and Leduc → MCCFR and Deep CFR on mini-drawmaha, each rung graded by an exact best response.
react python reinforcement-learning poker game-theory nash-equilibrium cfr counterfactual-regret-minimization deep-cfr mccfr
-
Updated
Nov 10, 2026 - Python
Add this topic to your repo
To associate your repository with the deep-cfr topic, visit your repo's landing page and select "manage topics."