The StarCraft Multi-Agent Challenge (SMAC) is a benchmark that provides elements of partial observability, challenging dynamics, and high-dimensional observation spaces. SMAC is built using the StarCraft II game engine, creating a testbed for research in cooperative MARL where each game unit is an independent RL agent.

CityFlow is a city-scale traffic camera dataset consisting of more than 3 hours of synchronized HD videos from 40 cameras across 10 intersections, with the longest distance between two simultaneous cameras being 2.5 km. The dataset contains more than 200K annotated bounding boxes covering a wide range of scenes, viewing angles, vehicle models, and urban traffic flow conditions. Camera geometry and calibration information are provided to aid spatio-temporal analysis. In addition, a subset of the benchmark is made available for the task of image-based vehicle re-identification (ReID). Source: CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

The StarCraft II Learning Environment (S2LE) is a reinforcement learning environment based on the game StarCraft II. The environment consists of three sub-components: a Linux StarCraft II binary, the StarCraft II API and PySC2. The StarCraft II API allows programmatic control of StarCraft II. It can be used to start a game, get observations, take actions, and review replays. PyC2 is a Python environment that wraps the StarCraft II API to ease the interaction between Python reinforcement learning agents and StarCraft II. It defines an action and observation specification, and includes a random agent and a handful of rule-based agents as examples. It also includes some mini-games as challenges and visualization tools to understand what the agent can see and do. Source: https://github.com/deepmind/pysc2 Image Source: https://github.com/deepmind/pysc2

The StarCraft Multi-Agent Challenges+ requires agents to learn completion of multi-stage tasks and usage of environmental factors without precise reward functions. The previous challenges (SMAC) recognized as a standard benchmark of Multi-Agent Reinforcement Learning are mainly concerned with ensuring that all agents cooperatively eliminate approaching adversaries only through fine manipulation with obvious reward functions. This challenge, on the other hand, is interested in the exploration capability of MARL algorithms to efficiently learn implicit multi-stage tasks and environmental factors as well as micro-control. This study covers both offensive and defensive scenarios. In the offensive scenarios, agents must learn to first find opponents and then eliminate them. The defensive scenarios require agents to use topographic features. For example, agents need to position themselves behind protective structures to make it harder for enemies to attack.

A new challenge domain with novel problems that arise from its combination of purely cooperative gameplay with two to five players and imperfect information. Source: The Hanabi Challenge: A New Frontier for AI Research

SMAC+ defensive armored scenario with sequential episodic buffer

smac+ defense infantry scenario with parallel episodic buffer

SMAC+ defensive infantry scenario with sequential episodic buffer

SMAC+ defensive outnumbered scenario with sequential episodic buffer

smac+ defense armored scenario with parallel episodic buffer

smac+ defense outnumbered scenario with parallel episodic buffer

smac+ offensive hard scenario with 20 parallel episodic buffer.

smac+ offensive scenario with 20 parallel episodic buffer.

smac+ offensive complicated scenario with 20 parallel episodic buffer.

SMAC+ offense distant scenario.

smac+ offensive near scenario with 20 parallel episodic buffer

Diverse datasets for offline multi-agent reinforcement learning research. Includes datasets for popular MARL benchmark environments such as: * MAMuJoCo * SMAC v1 & v2 * PettingZoo * FlatLand * CityLearn

SMAC+ offensive complicated scenario with sequential episodic buffer

SMAC+ offensive distant scenario with sequential episodic buffer

SMAC+ offensive hard scenario with sequential episodic buffer

SMAC+ offensive near scenario with sequential episodic buffer

SMAC+ offensive superhard scenario with sequential episodic buffer

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

ColosseumRL is a framework for research in reinforcement learning in n-player games. ColosseumRL contains a number of multiagent free-for-all games. Currently, we have Tron, Blokus, and 3 and 4-player tic-tac-toe. In the future, we will be adding Chinese checkers and other similar games. Tron is a fully-observable multiagent free-for-all turn-based snake variant where players try to survive the longest without crashing into walls or each other. Blokus is a fully-observable multiagent free-for-all turn-based game in which players place pieces on a board to claim space and strategically block opponents from placing their own pieces.

Multi-agent pursuit in matrix world (pursuitMW) is a partially observable Markov game (POMG) between a swarm of pursuers and a swarm of evaders. Algorithms can be developed for the pursuers, evaders, or both of them.

The Room environment - v0 DOI We have released a challenging Gymnasium compatible environment. The best strategy for this environment is to have both episodic and semantic memory systems. See the paper for more information. ## Prerequisites 1. A unix or unix-like x86 machine 1. python 3.10 or higher. 1. Running in a virtual environment (e.g., conda, virtualenv, etc.) is highly recommended so that you don't mess up with the system python. 1. This env is added to the PyPI server. Just run: pip install room-env ## Data collection Data is collected from querying ConceptNet APIs. For simplicity, we only collect triples whose format is (head, atlocation, tail). Here head is one of the 80 MS COCO dataset categories. This was kept in mind so that later on we can use images as well. If you want to collect the data manually, then run below: python collect_data.py ## How does this environment work? The Gymnasium-compatible Room environment is one big room with N_people number of people who can freely move around. Each of them selects one object, among N_objects, and places it in one of the N_locations locations. N_agents number of agent(s) are also in this room. They can only observe one human placing an object, one at a time; x^(t). At the same time, they are given one question about the location of an object; q^(t). x^(t) is given as a quadruple, (h^(t),r^(t),t^(t),t), For example, <James’s laptop, atlocation, James’s desk, 42> accounts for an observation where an agent sees James placing his laptop on his desk at t = 42. q^(t) is given as a double, (h,r). For example, <Karen’s cat, atlocation> is asking where Karen’s cat is located. If the agent answers the question correctly, it gets a reward of + 1, and if not, it gets 0. The reason why the observations and questions are given as RDF-triple-like format is two folds. One is that this structured format is easily readable / writable by both humans and machines. Second is that we can use existing knowledge graphs, such as ConceptNet . To simplify the environment, the agents themselves are not actually moving, but the room is continuously changing. There are several random factors in this environment to be considered: 1. With the chance of p_commonsense, a human places an object in a commonsense location (e.g., a laptop on a desk). The commonsense knowledge we use is from ConceptNet. With the chance of 1 − p_commonsense, an object is placed at a non-commonsense random location (e.g., a laptop on the tree). 1. With the chance of p_{new_location}, a human changes object location. 1. With the chance of p_{new_object}, a human changes his/her object to another one. 1. With the chance of p_{switch_person}, two people switch their locations. This is done to mimic an agent moving around the room. All of the four probabilities account for the Bernoulli distributions. Consider there is only one agent. Then this is a POMDP, where S_t = (x^(t), q^(t)), A_t = (do something with x^(t), answer q^(t)), and R_t ∈ {0, 1}. Currently there is no RL trained for this. We only have some heuristics. Take a look at the paper for more details. ## RoomEnv-v0 python import gymnasium as gym env = gym.make("room_env:RoomEnv-v0") (observation, question), info = env.reset() rewards = 0 while True: (observation, question), reward, done, truncated, info = env.step("This is my answer!") rewards += reward if done: break print(rewards) Every time when an agent takes an action, the environment will give you an observation and a question to answer. You can try directly answering the question, such as env.step("This is my answer!"), but a better strategy is to keep the observations in memory systems and take advantage of the current observation and the history of them in the memory systems. Take a look at this repo for an actual interaction with this environment to learn a policy. ## Contributing Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated. 1. Fork the Project 1. Create your Feature Branch (git checkout -b feature/AmazingFeature) 1. Run make test && make style && make quality in the root repo directory, to ensure code quality. 1. Commit your Changes (git commit -m 'Add some AmazingFeature') 1. Push to the Branch (git push origin feature/AmazingFeature) 1. Open a Pull Request ## Cite our paper bibtex @misc{https://doi.org/10.48550/arxiv.2204.01611, doi = {10.48550/ARXIV.2204.01611}, url = {https://arxiv.org/abs/2204.01611}, author = {Kim, Taewoon and Cochez, Michael and Francois-Lavet, Vincent and Neerincx, Mark and Vossen, Piek}, keywords = {Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {A Machine With Human-Like Memory Systems}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ## Authors - Taewoon Kim - Michael Cochez - Vincent Francois-Lavet - Mark Neerincx - Piek Vossen ## License MIT