benzyx / DomRL
DomRL is a simulation environment for the card game Dominion, created by Donald X Vaccarino, meant to simplify the development and testing of various AI strategies, specifically Reinforcement Learning algorithms.
☆17Updated 4 years ago
Alternatives and similar repositories for DomRL:
Users that are interested in DomRL are comparing it to the libraries listed below
- The code used to power DeepRole☆35Updated 2 years ago
- Research code implementing the search AI agent for Hanabi, as well as a web server so people can play against it☆128Updated last year
- Opinionated library for managing hyperparameters and mutable state of machine learning training systems.☆19Updated last year
- Scalable implementation of DREAM - Deep RL for multi-agent imperfect information games☆115Updated 9 months ago
- ReconChess python implementation☆42Updated 3 years ago
- Scaling scaling laws with board games.☆48Updated last year
- 🃏♠️♥️♦️♣️☆27Updated 4 years ago
- [AutoML'22] Bayesian Generational Population-based Training (BG-PBT)☆28Updated 2 years ago
- Scalable Implementation of Neural Fictitous Self-Play☆77Updated 6 years ago
- Rainbow DQN implementation accompanying the paper "Fast and Data-Efficient Training of Rainbow" which reaches 205.7 median HNS after 10M …☆45Updated 3 years ago
- A number of agents (PPO, MuZero) with a Perceiver-based NN architecture that can be trained to achieve goals in nethack/minihack environm…☆41Updated 2 years ago
- Reinforcement learning in pure JAX.☆12Updated 2 months ago
- PyTorch AlphaZero implementation with multiplayer support [NeurIPS 2019 Deep Reinforcement Learning Workshop]☆34Updated 4 years ago
- Deep reinforcement learning implementation that trains AIs for the CodeCraft real-time strategy game.☆21Updated last year
- A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each othe…☆157Updated 4 years ago
- Code to accompany "Human-Level Performance in No-Press Diplomacy via Equilibrium Search", published at ICLR 2021☆47Updated 2 years ago
- ☆53Updated last year
- ☆299Updated 4 months ago
- Cythonized versions of the OpenAI Gym classic control environments.☆12Updated 5 years ago
- [WIP] Highly customizable rogue-like game for AI expmeriments☆81Updated last year
- ☆20Updated 5 years ago
- fast + parallel AlphaZero in JAX☆95Updated 4 months ago
- ☆31Updated 2 years ago
- State of the art Hanabi bots + simulation framework in rust☆45Updated last year
- cfrx is a collection of algorithms and tools for hardware-accelerated Counterfactual Regret Minimization (CFR) algorithms in Jax.☆31Updated 8 months ago
- Implicit Normalizing Flows + Reinforcement Learning☆61Updated 5 years ago
- Learning to play Settlers of Catan with Deep RL - custom training environment and implementation of PPO☆85Updated 3 years ago
- A working AlphaZero implementation that's simple enough to be able to understand what's going on at a quick glance, without sacrificing t…☆13Updated 2 years ago
- Read Google Cloud Storage, Azure Blobs, and local paths with the same interface☆63Updated 8 months ago
- Accelerated replay buffers in JAX☆41Updated 2 years ago