2019

The Multi-Agent Reinforcement Learning in Malm\"O (MARL\"O) Competition

Perez-Liebana, Diego, Hofmann, Katja, Mohanty, Sharada Prasanna et al.

Understand

Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types.

The Multi-Agent Reinforcement Learning in Malm\"O (MARL\"O) competition is a new challenge that proposes research in this domain using multiple 3D games.
The goal of this contest is to foster research in general agents that can learn across different games and opponent types, proposing a challenge as a milestone in the direction of Artificial General Intelligence.

Built on

Stochastic games
Shapley, L. S. (1953) · 1953
Earlier work this paper cites.
Multi-agent reinforcement learning: independent versus cooperative agents
Tan, M. (1993) · 1993
Earlier work this paper cites.
Markov games as a framework for multi-agent reinforcement learning
Littman, M. L. (1994) · 1994
Earlier work this paper cites.
Multiagent systems: A survey from a machine learning perspective
Stone, P. and Veloso, M. (2000) · 2000
Earlier work this paper cites.

Similar

Multi-agent reinforcement learning: A survey
Busoniu, L., Babuska, R., and De Schutter, B. (2006) · 2006
Cited alongside, same era.
Game theory of mind
Yoshida, W., Dolan, R. J., and Friston, K. J. (2008) · 2008
Cited alongside, same era.
General Video Game AI: Competition, Challenges and Opportunities
Perez-Liebana, D., Samothrakis, S., Togelius, J., Lucas, S. M., and Schaul, T. (2016) · 2016
Cited alongside, same era.
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Lowe, R., WU, Y., Tamar, A., Harb, J., Abbeel, O. P., and Mordatch, I. (2017) · 2017
Cited alongside, same era.
Counterfactual multi-agent policy gradients
Original
Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., and Whiteson, S. (2017a)
Cited in the paper.
Stabilising experience replay for deep multi-agent reinforcement learning
Foerster, J., Nardelli, N., Farquhar, G., Afouras, T., Torr, P. H., Kohli, P., and Whiteson, S. (2017b)
Cited in the paper.

Then

Value-Decomposition Networks For Cooperative Multi-Agent Learning
Original
Sunehag, P., Lever, G., Gruslys, A., Czarnecki, W. M., Zambaldi, V., Jaderberg, M., Lanctot, M., Sonnerat, N., Leibo, J. Z., Tuyls, K., and Graepel, T. (2017) · 2017
Later among the works it cites.
Learning to Run
Laboratory, S. N. B. (2017) · 2018
Later among the works it cites.
The Malmo Collaborative AI Challenge
Research, M. (2017) · 2018
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv