init

Makefile

@@ -0,0 +1,26 @@
+#.PHONY: test-training-agent-interface
+#test-training-agent-interface:
+#	PYTHONHASHSEED=24 pytest -v
+#
+#.PHONY: test-learning
+#test-learning:
+#
+#.PHONY: profiling
+#profiling:
+
+.PHONY: clean
+clean:
+	rm -rf ./logs/*
+
+.PHONY: format
+format:
+	# pip install black==20.8b1
+	black .
+
+.PHONY: docs
+docs:
+	(cd docs; make clean html)
+
+.PHONY: rm-pycache
+rm-pycache:
+	find . -type f -name '*.py[co]' -delete -o -type d -name __pycache__ -delete

README.md

@@ -1,2 +1,64 @@
-# malib
+# MALib
 A general-purpose multi-agent training framework.
+
+## Installation
+
+**step1: build environment**
+
+```shell
+conda create -n malib python==3.7 -y
+conda activate malib
+pip install -e .
+
+# for development
+pip install -e .[dev]
+```
+**step2: install openspiel**
+
+installation guides: [openspiel](https://github.com/deepmind/open_spiel)
+
+## Quick Start
+
+```python
+"""PSRO with PPO for Leduc Holdem"""
+
+from malib.envs.poker import poker_aec_env as leduc_holdem
+from malib.runner import run
+from malib.rollout import rollout_func
+
+
+env = leduc_holdem.env(fixed_player=True)
+
+run(
+    agent_mapping_func=lambda agent_id: agent_id,
+    env_description={
+        "creator": leduc_holdem.env,
+        "config": {"fixed_player": True},
+        "id": "leduc_holdem",
+        "possible_agents": env.possible_agents,
+    },
+    training={
+        "interface": {
+            "type": "independent",
+            "observation_spaces": env.observation_spaces,
+            "action_spaces": env.action_spaces
+        },
+    },
+    algorithms={
+        "PSRO_PPO": {
+            "name": "PPO",
+            "custom_config": {
+                "gamma": 1.0,
+                "eps_min": 0,
+                "eps_max": 1.0,
+                "eps_decay": 100,
+            },
+        }
+    },
+    rollout={
+        "type": "async",
+        "stopper": "simple_rollout",
+        "callback": rollout_func.sequential
+    }
+)
+```

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/source/api/modules.rst

@@ -0,0 +1,7 @@
+MALib
+=====
+
+.. toctree::
+   :maxdepth: 2
+
+   malib

docs/source/conf.py

@@ -0,0 +1,85 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+import inspect
+import shutil
+
+
+__location__ = os.path.dirname(
+    os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+)
+
+sys.path.insert(0, __location__)
+
+
+# -- Project information -----------------------------------------------------
+
+project = "MALib"
+copyright = "2021, SJTU-MARL"
+author = "SJTU-MARL"
+
+# The full version, including alpha/beta/rc tags
+release = "v0.1.0"
+
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx_rtd_theme",  # theme
+    "sphinx.ext.autodoc",  # automatically extract docs from docstrings
+    "sphinx.ext.coverage",  # make coverage generates documentation coverage reports
+    "sphinx.ext.viewcode",  # link to sourcecode from docs
+    # "sphinx.ext.grahviz", # graphviz
+    "sphinxcontrib.apidoc",
+]
+
+apidoc_module_dir = os.path.join(__location__, "malib")
+apidoc_exclude_paths = ["setup.py"]
+apidoc_module_first = True
+apidoc_extra_args = [
+    "--force",
+    "--separate",
+    "--ext-viewcode",
+    "--doc-project=MALib",
+    "--maxdepth=2",
+]
+
+exclude_patterns = ["tests/", "test*.py", "envs/multiagent_mujoco", "envs/star_craft2"]
+
+# ensure __init__ is always documented
+autoclass_content = "both"
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = []
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+# html_theme = 'alabaster'
+html_theme = "sphinx_rtd_theme"
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]

docs/source/index.rst

@@ -0,0 +1,19 @@
+.. MALib documentation master file, created by
+   sphinx-quickstart on Mon Apr 26 17:29:10 2021.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to MALib's documentation!
+=================================
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

examples/appo_simple.py

@@ -0,0 +1,71 @@
+import argparse
+
+from pettingzoo.mpe import simple_v2
+
+from malib.runner import run
+
+
+parser = argparse.ArgumentParser("Async PPO training on mpe environments.")
+
+parser.add_argument("--num_learner", type=int, default=3)
+parser.add_argument("--batch_size", type=int, default=64)
+parser.add_argument("--num_epoch", type=int, default=100)
+parser.add_argument("--algorithm", type=str, default="DQN")
+parser.add_argument("--rollout_metric", type=str, default="simple", choices={"simple"})
+
+
+if __name__ == "__main__":
+    args = parser.parse_args()
+    env_config = {
+        "max_cycles": 25,
+    }
+    env = simple_v2.env(**env_config)
+    possible_agents = env.possible_agents
+    observation_spaces = env.observation_spaces
+    action_spaces = env.action_spaces
+
+    run(
+        group="MPE/simple",
+        name="async_ppo",
+        worker_config={"worker_num": args.num_learner},
+        env_description={
+            "creator": simple_v2.env,
+            "config": env_config,
+            "id": "simple_v2",
+            "possible_agents": possible_agents,
+        },
+        agent_mapping_func=lambda agent: [
+            f"{agent}_async_{i}" for i in range(args.num_learner)
+        ],
+        training={
+            "interface": {
+                "type": "async",
+                "observation_spaces": observation_spaces,
+                "action_spaces": action_spaces,
+                "population_size": -1,
+            },
+            "config": {
+                "update_interval": 1,
+                "saving_interval": 10,
+                "batch_size": args.batch_size,
+                "num_epoch": 100,
+            },
+        },
+        algorithms={
+            "Async": {"name": args.algorithm},
+        },
+        rollout={
+            "type": "async",
+            "stopper": "simple_rollout",
+            "metric_type": args.rollout_metric,
+            "fragment_length": env_config["max_cycles"],
+            "num_episodes": 100,  # episode for each evaluation/training epoch
+            "terminate": "any",
+            "callback": "sequential",
+        },
+        global_evaluator={
+            "name": "generic",
+            "config": {"stop_metrics": {}},
+        },
+        dataset_config={"episode_capacity": 30000},
+    )

examples/configs/__init__.py

@@ -0,0 +1,8 @@
+# -*- coding:utf-8 -*-
+# Create Date: 5/1/21, 3:31 PM
+# Author: ming
+# ---
+# Last Modified: 5/1/21
+# Modified By: ming
+# ---
+# Copyright (c) 2020 MARL @ SJTU