diplomacy / research
Supervised and RL Models for No Press Diplomacy
☆62Updated last year
Alternatives and similar repositories for research:
Users that are interested in research are comparing it to the libraries listed below
- ☆50Updated 8 months ago
- Diplomacy: DATC-Compliant Game Engine with Web Interface☆107Updated 11 months ago
- Nethack Learning Environment Wrapper for Language Interface☆35Updated last year
- we're building an AI to play the board game Diplomacy!☆29Updated 2 years ago
- Code for magnetic mirror descent.☆15Updated last year
- Code to accompany "Human-Level Performance in No-Press Diplomacy via Equilibrium Search", published at ICLR 2021☆45Updated 2 years ago
- Gridworld for MARL experiments☆138Updated 3 years ago
- ☆293Updated 3 weeks ago
- PAIRED in PyTorch 🔥☆57Updated last year
- PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tu…☆133Updated last year
- Code release for Learning with Opponent-Learning Awareness and variations.☆147Updated last year
- The code used to power DeepRole☆35Updated 2 years ago
- Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning☆98Updated 2 years ago
- ReconChess python implementation☆42Updated 2 years ago
- A grid-world game engine for game AI research☆236Updated 9 months ago
- Deep RL Code for XDO: A Double Oracle Algorithm for Extensive-Form Games☆37Updated 3 years ago
- Implementation of the Off Belief Learning algorithm.☆46Updated 2 years ago
- Arena: A General Evaluation Platform and Building Toolkit for Single/Multi-Agent Intelligence. AAAI 2020.☆101Updated last week
- impact-driven-exploration☆130Updated last year
- Arena: A General Evaluation Platform and Building Toolkit for Single/Multi-Agent Intelligence. AAAI 2020.☆81Updated 3 years ago
- Synchronized Curriculum Learning for RL Agents☆31Updated this week
- Hierarchical Self-Play☆21Updated 6 years ago
- ☆46Updated 7 months ago
- A gym interface for AI safety gridworlds created in pycolab.☆17Updated 2 years ago
- Novelty MiniGrid--NovGrid--is an extension of MiniGrid environment that allows for the world properties and dynamics to change according …☆35Updated 7 months ago
- A toolbox with the goal of speeding up research on bargaining in MARL (cooperation problems in MARL).☆31Updated 2 years ago
- Emergence of complex strategies through multiagent competition☆42Updated 2 years ago
- Gridworld domains in the gym interface☆27Updated 3 months ago
- ☆9Updated 3 years ago
- Implementation of the Box-World environment from the paper "Relational Deep Reinforcement Learning"☆45Updated last year