More Like this

1. Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games

   Mcaleer, Stephen; Lanier, JB; Fox, Roy; Baldi, Pierre (January 2020, Advances in neural information processing systems)

   challenging when the number of information states is large. Policy Space Response Oracles (PSRO) is a deep reinforcement learning algorithm grounded in game theory that is guaranteed to converge to an approximate Nash equilibrium. However, PSRO requires training a reinforcement learning policy at each iteration, making it too slow for large games. We show through counterexamples and experiments that DCH and Rectified PSRO, two existing approaches to scaling up PSRO, fail to converge even in small games. We introduce Pipeline PSRO (P2SRO), the first scalable PSRO-based method for finding approximate Nash equilibria in large zero-sum imperfect-information games. P2SRO is able to parallelize PSRO with convergence guarantees by maintaining a hierarchical pipeline of reinforcement learning workers, each training against the policies generated by lower levels in the hierarchy. We show that unlike existing methods, P2SRO converges to an approximate Nash equilibrium, and does so faster as the number of parallel workers increases, across a variety of imperfect information games. We also introduce an open-source environment for Barrage Stratego, a variant of Stratego with an approximate game tree complexity of 1050. P2SRO is able to achieve state-of-theart performance on Barrage Stratego and beats all existing bots. Experiment code is available at https://github.com/JBLanier/pipeline-psro. 

   more » « less
2. Cooperative Control of Mobile Robots with Stackelberg Learning

   Joewie J. Koh, Guohui Ding (October 2020, Intelligent robots and systems)

   null (Ed.)

   Multi-robot cooperation requires agents to make decisions that are consistent with the shared goal without disregarding action-specific preferences that might arise from asymmetry in capabilities and individual objectives. To accomplish this goal, we propose a method named SLiCC: Stackelberg Learning in Cooperative Control. SLiCC models the problem as a partially observable stochastic game composed of Stackelberg bimatrix games, and uses deep reinforcement learning to obtain the payoff matrices associated with these games. Appropriate cooperative actions are then selected with the derived Stackelberg equilibria. Using a bi-robot cooperative object transportation problem, we validate the performance of SLiCC against centralized multi-agent Q-learning and demonstrate that SLiCC achieves better combined utility. 

   more » « less
3. Rotation, Translation, and Cropping for Zero-Shot Generalization

   https://doi.org/10.1109/CoG47356.2020.9231907  

   Ye, Chang; Khalifa, Ahmed; Bontrager, Philip; Togelius, Julian (August 2020, IEEE Conference on Games)

   null (Ed.)

   Deep Reinforcement Learning (DRL) has shown im- pressive performance on domains with visual inputs, in particular various games. However, the agent is usually trained on a fixed environment, e.g. a fixed number of levels. A growing mass of evidence suggests that these trained models fail to generalize to even slight variations of the environments they were trained on. This paper advances the hypothesis that the lack of generalization is partly due to the input representation, and explores how rotation, cropping and translation could increase generality. We show that a cropped, translated and rotated observation can get better generalization on unseen levels of two-dimensional arcade games from the GVGAI framework. The generality of the agents is evaluated on both human-designed and procedurally generated levels. 

   more » « less
4. Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning

   McAleer, S; Farina, G; Zhou, G; Wang, M; Yang, Y; Sandholm, T (December 2023, NeurIPS23)

   Recent algorithms have achieved superhuman performance at a number of twoplayer zero-sum games such as poker and go. However, many real-world situations are multi-player games. Zero-sum two-team games, such as bridge and football, involve two teams where each member of the team shares the same reward with every other member of that team, and each team has the negative of the reward of the other team. A popular solution concept in this setting, called TMECor, assumes that teams can jointly correlate their strategies before play, but are not able to communicate during play. This setting is harder than two-player zerosum games because each player on a team has different information and must use their public actions to signal to other members of the team. Prior works either have game-theoretic guarantees but only work in very small games, or are able to scale to large games but do not have game-theoretic guarantees. In this paper we introduce two algorithms: Team-PSRO, an extension of PSRO from twoplayer games to team games, and Team-PSRO Mix-and-Match which improves upon Team PSRO by better using population policies. In Team-PSRO, in every iteration both teams learn a joint best response to the opponent’s meta-strategy via reinforcement learning. As the reinforcement learning joint best response approaches the optimal best response, Team-PSRO is guaranteed to converge to a TMECor. In experiments on Kuhn poker and Liar’s Dice, we show that a tabular version of Team-PSRO converges to TMECor, and a version of Team PSRO using deep cooperative reinforcement learning beats self-play reinforcement learning in the large game of Google Research Football. 

   more » « less
5. Semicentralized Deep Deterministic Policy Gradient in Cooperative StarCraft Games

   https://doi.org/10.1109/TNNLS.2020.3042943  

   Xie, Dong; Zhong, Xiangnan (December 2020, IEEE Transactions on Neural Networks and Learning Systems)

   null (Ed.)

   In this article, we propose a novel semicentralized deep deterministic policy gradient (SCDDPG) algorithm for cooperative multiagent games. Specifically, we design a two-level actor-critic structure to help the agents with interactions and cooperation in the StarCraft combat. The local actor-critic structure is established for each kind of agents with partially observable information received from the environment. Then, the global actor-critic structure is built to provide the local design an overall view of the combat based on the limited centralized information, such as the health value. These two structures work together to generate the optimal control action for each agent and to achieve better cooperation in the games. Comparing with the fully centralized methods, this design can reduce the communication burden by only sending limited information to the global level during the learning process. Furthermore, the reward functions are also designed for both local and global structures based on the agents' attributes to further improve the learning performance in the stochastic environment. The developed method has been demonstrated on several scenarios in a real-time strategy game, i.e., StarCraft. The simulation results show that the agents can effectively cooperate with their teammates and defeat the enemies in various StarCraft scenarios. 

   more » « less