Skip to main content

Google Research Football : RL

by Karol Kurach, Research Lead and Olivier Bachem, Research Scientist, Google Research, Zürich

Abstract

Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible manner. We introduce the Google Research Football Environment, a new reinforcement learning environment where agents are trained to play football in an advanced, physics-based 3D simulator. The resulting environment is challenging, easy to use and customize, and it is available under a permissive open-source license. In addition, it provides support for multiplayer and multi-agent experiments. We propose three full-game scenarios of varying difficulty with the Football Benchmarks and report baseline results for three commonly used reinforcement algorithms (IMPALA, PPO, and Ape-X DQN). We also provide a diverse set of simpler scenarios with the Football Academy and showcase several promising research directions.

The goal of reinforcement learning (RL) is to train smart agents that can interact with their environment and solve complex tasks, with real-world applications towards robotics, self-driving cars, and more. The rapid progress in this field has been fueled by making agents play games such as the iconic Atari console games, the ancient game of Go, or professionally played video games like Dota 2 or Starcraft 2, all of which provide challenging environments where new algorithms and ideas can be quickly tested in a safe and reproducible manner. The game of football is particularly challenging for RL, as it requires a natural balance between short-term control, learned concepts, such as passing, and high-level strategy.

Google announced the release of the Google Research Football Environment, a novel RL environment where agents aim to master the world’s most popular sport—football. Modelled after popular football video games, the Football Environment provides a physics-based 3D football simulation where agents control either one or all football players on their team, learn how to pass between them, and manage to overcome their opponent’s defence in order to score goals. 

The Football Environment provides several crucial components: 
  • a highly-optimized game engine, 
  • a demanding set of research problems called Football Benchmarks, 
  • the Football Academy, a set of progressively harder RL scenarios. 



Football Engine 

The core of the Football Environment is an advanced football simulation, called Football Engine, which is based on a heavily modified version of Gameplay Football. Based on input actions for the two opposing teams, it simulates a match of football including goals, fouls, corner and penalty kicks, and offsides. The Football Engine is written in highly optimized C++ code, allowing it to be run on off-the-shelf machines, both with GPU and without GPU-based rendering enabled. This allows it to reach a performance of approximately 25 million steps per day on a single Hexa-core machine.



The Football Engine is an advanced football simulation that supports all the major football rules such as kickoffs (top left), goals (top right), fouls, cards (bottom left), corner and penalty kicks (bottom right), and offside.

The Football Engine has additional features geared specifically towards RL. First, it allows learning from both different state representations, which contain semantic information such as the player’s locations, as well as learning from raw pixels. Second, to investigate the impact of randomness, it can be run in both a stochastic mode (enabled by default), in which there is randomness in both the environment and opponent AI actions and in a deterministic mode, where there is no randomness. Third, the Football Engine is out of the box compatible with the widely used OpenAI Gym API. Finally, researchers can get a feeling for the game by playing against each other or their agents, using either keyboards or gamepads.

Football Benchmarks

With the Football Benchmarks, we propose a set of benchmark problems for RL research based on the Football Engine. The goal in these benchmarks is to play a “standard” game of football against a fixed rule-based opponent that was hand-engineered for this purpose. We provide three versions: the Football Easy Benchmark, the Football Medium Benchmark, and the Football Hard Benchmark, which only differ in the strength of the opponent. 

As a reference, They provide benchmark results for two state-of-the-art reinforcement learning algorithms: DQN and IMPALA, which both can be run in multiple processes on a single machine or concurrently on many machines. We investigate both the setting where the only rewards provided to the algorithm are the goals scored and the setting where we provide additional rewards for moving the ball closer to the goal. 

Results indicate that the Football Benchmarks are interesting research problems of varying difficulties. In particular, the Football Easy Benchmark appears to be suitable for research on single-machine algorithms while the Football Hard Benchmark proves to be challenging even for massively distributed RL algorithms. Based on the nature of the environment and the difficulty of the benchmarks.

Football Academy & Future Directions

As training agents for the full Football Benchmarks can be challenging, They provide Football Academy, a diverse set of scenarios of varying difficulty. This allows researchers to get the ball rolling on new research ideas, allows testing of high-level concepts (such as passing), and provides a foundation to investigate curriculum learning research ideas, where agents learn from progressively harder scenarios. Examples of the Football Academy scenarios include settings where agents have to learn how to score against the empty goal, where they have to learn how to quickly pass between players, and where they have to learn how to execute a counter-attack. Using a simple API, researchers can further define their own scenarios and train agents to solve them.


Comments

Popular posts from this blog

Detecting Anomaly in Big Data System Logs Using Convolutional Neural Network

By - Siyang Lu, Xiang Wei, Yandong Li, Liqiang Wang Department of Computer Science, University of Central Florida, Orlando, FL, USA School of Software Engineering, Beijing Jiaotong University, China Paper Link Previous week we did a scan of the survey of Anomaly detection   , that covers breath of the topic (Types of Anomalies, Types of Models and their applications). In this summary paper, we look in to the core Heavy lifting part of Detecting Anomaly in Big Data System Logs Using Convolutional Neural Network. Abstract Nowadays, big data systems are being widely adopted by many domains for offering effective data solutions, such as manufacturing, healthcare, education, and media. Big data systems produce tons of unstructured logs that contain buried valuable information. However, it is a daunting task to manually unearth the information and detect system anomalies. A few automatic methods have been developed, where the cutting-edge machine lear...

DDSP: DIFFERENTIABLE DIGITAL SIGNAL PROCESSING

 -By Google Research {jesseengel,hanoih,gcj,adarob}@google.com Paper Link Code Demo Abstract Most generative models of audio directly generate samples in one of two domains: time or frequency. While sufficient to express any signal, these representations are inefficient, as they do not utilize existing knowledge of how sound is generated and perceived. A third approach (vocoders/synthesizers) successfully incorporates strong domain knowledge of signal processing and perception, but has been less actively researched due to limited expressivity and difficulty integrating with modern auto-differentiation-based machine learning methods. In this paper, we introduce the Differentiable Digital Signal Processing (DDSP) library, which enables direct integration of classic signal processing elements with deep learning methods. Focusing on audio synthesis, we achieve high-fidelity generation without the need for large autoregressive models or adversarial losses, demonstrating that DDSP enable...

Capsule Neural Networks

-By Sara Sabour, Nicholas Frosst,  Geoffrey E. Hinton  Google Brain Toronto Paper Link Abstract   A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters. Active capsules at one level make predictions, via transformation matrices, for the instantiation parameters of higher-level capsules. When multiple predictions agree, a higher level capsule becomes active. We show that a discrimininatively trained, multi-layer capsule system achieves state-of-the-art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits. To achieve these results we use an iterative routing-by-agreement mechanism: A lower-level capsule prefers to send its output to higher...