paper-with-me

Papers

Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

2018-11-30 · ICLR 2018 1 · Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Dan Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to employ encoder-decoder neural networks for this task, and introduce proxy tasks and baselines for evaluation to assess their ability of capturing basic game rules and high-level dynamics. By combining convolutional neural networks and recurrent networks, we exploit spatial and sequential correlations and train well-performing models on a large dataset of human games of StarCraft: Brood War. Finally, we demonstrate the relevance of our models to downstream tasks by applying them for enemy unit prediction in a state-of-the-art, rule-based StarCraft bot. We observe improvements in win rates against several strong community bots.

📄 PDF Abstract BibTeX arXiv:1812.00054

Code (1)

facebookresearch/starcraft_defogger 공식 구현 pytorch

Tasks

DecoderReal-Time Strategy GamesStarcraftState Estimation

Similar Papers 제목 키워드 기반

Solving Large Extensive-Form Games with Strategy Constraints

2018-09-20 · Trevor Davis, Kevin Waugh, Michael Bowling

Extensive-form games are a common model for multiagent interactions with imperfect information. In two-player zero-sum games, the typical solution concept is a Nash equilibrium over the unconstrained strategy set for eac…

counterfactualForm

Security Games with Information Leakage: Modeling and Computation

2015-04-23 · Haifeng Xu, Albert X. Jiang, Arunesh Sinha, Zinovi Rabinovich 외

Most models of Stackelberg security games assume that the attacker only knows the defender's mixed strategy, but is not able to observe (even partially) the instantiated pure strategy. Such partial observation of the dep…

Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations

2020-02-23 · ICLR 2020 1 · Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee 외

Deep reinforcement learning is successful in decision making for sophisticated games, such as Atari, Go, etc. However, real-world decision making often requires reasoning with partial information extracted from complex v…

Atari GamesDecision MakingDeep Reinforcement Learningreinforcement-learning+3

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations

2026-09-17 · Kevin Qu, Tao Sun, Massimiliano Viola, Liyuan Zhu 외 hf

Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from a single observation a…

Point Clouds

High-Level Strategy Selection under Partial Observability in StarCraft: Brood War

2018-11-21 · Jonas Gehring, Da Ju, Vegard Mella, Daniel Gant 외

We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action corresponds to switching to the respective…

Real-Time Strategy Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2