janrvdolf / gpucfr
GPUCFR is a parallel implementation of Counterfactual Regret Minimization (CFR) in C++ and CUDA C for NVIDIA GPUs.
☆19Updated 3 years ago
Related projects: ⓘ
- ☆54Updated 3 months ago
- A NLTH Poker Agent using Counterfactual Regret Minimization☆47Updated 4 years ago
- Implementations of CFR for solving a variety of Holdem-like poker games☆133Updated last year
- Python implementation of Deepstack☆79Updated 4 years ago
- An attempt at a Python implementation of Pluribus, a No-Limits Hold'em Poker Bot☆100Updated 3 years ago
- This code is based on the implementation of http://www.cs.cmu.edu/afs/cs/Web/People/sandholm/potential-aware_imperfect-recall.aaai14.pdf,…☆36Updated 5 years ago
- ☆27Updated 2 years ago
- k-means clustering for poker hands based on earth mover's distance (EMD)☆14Updated 4 years ago
- ☆203Updated 5 years ago
- An open implementation of Pure CFR applied to ACPC poker games.☆200Updated 7 years ago
- ☆31Updated 5 years ago
- ☆32Updated 4 years ago
- poker ai☆29Updated 2 years ago
- C++ implementations of Counterfactual Regret Minimization and Monte Carlo CFR☆71Updated 2 years ago
- ☆65Updated 7 months ago
- Rails application that allows humans to play poker matches managed by the Annual Computer Poker Competition's Dealer program in a web GUI…☆55Updated 7 years ago
- A C library for indexing poker hands that respects suit isomorphisms☆63Updated 10 years ago
- Scalable Implementation of Deep CFR and Single Deep CFR☆273Updated 4 years ago
- Potential-Aware Imperfect-Recall Abstraction with Earth Mover’s Distance in Imperfect-Information Games☆15Updated 5 years ago
- Scalable Implementation of Neural Fictitous Self-Play☆71Updated 5 years ago
- DeeperStacker: DeepHoldem Evil Brother☆38Updated 3 years ago
- ☆17Updated 4 years ago
- A poker AI for NL Texas Holdem trained using Monte-Carlo Counterfactual Regret Minimization.☆85Updated 2 years ago
- A python implementation of Counterfactual Regret Minimization for poker☆274Updated 9 years ago
- Implementation of Pluribus by Noam Brown & Tuomas Sandholm, introduced in the paper "Superhuman AI for multiplayer poker".☆15Updated 2 years ago
- This is an implementation of DeepStack for No Limit Texas Hold'em, extended from DeepStack-Leduc.☆24Updated 5 years ago
- A Deep Reinforcment Learning Aproach to Texas Holdem☆30Updated 2 years ago
- Implementation of Pluribus by Noam Brown & Tuomas Sandholm, a Superhuman AI for 6-MAX No-Limit Holdem Poker Bot.☆212Updated 3 years ago
- Parsing the hand histories that poker AI Pluribus played☆74Updated 4 years ago
- Framework for Multi-Agent Deep Reinforcement Learning in Poker☆406Updated last year