All posts by AIMS


As part of Industry week, we had the opportunity to visit Nvidia in Reading.  We had a great day, and learnt about AI at the Edge, NVIDIA’s AI Platform, JADE & Tesla, and had demonstrations on Jetson inferenecing & TensorRT.

Read More

Paper addressing multi-agent AI problems wins top accolade

Paper addressing multi-agent AI problems wins top accolade

The winning paper ‘Counterfactual Multi-Agent Policy Gradients’ (COMA) presents a method which could soon make it possible to deploy learning multi-agent systems in the real world.

COMA differs from a lot artificial intelligence research by focussing on multi-agent problems, rather than single agent setting and two player games. There are many challenging multi-agent problems to tackle, ranging from self-driving cars to drones and even social interactions. In many of these applications a number of independent entities needs to be able to take independent actions based on local observations in order to achieve a common goal.

For example, in a fleet of search-and-rescue drones each single drone typically needs to be able to decide on its best course of action using only local information. This is commonly referred to as ‘decentralised execution’. However, often the design of the policies can be carried out in a centralised fashion, for example when training of the policies is carried out using a simulator which has access to the observations and actions of all agents. The research team believes that this domain of centralised training and decentralised execution is one of the key avenues for successfully developing and deploying multi-agent systems in the real world.

One of the great challenges when training multi-agent policies is the credit assignment problem. Just like in a football team, the reward achieved depends on the actions of all of the different agents. Given that all agents are constantly improving their policies, it is difficult for any given agent to evaluate the impact of their individual action on the overall performance of the team. To address this issue, the research team (Computer Science’s Jakob N. Foerster, Gregory Farquhar (CDT in AIMS) and Professor Shimon Whiteson, with Engineering Science’s Triantafyllos Afouras ( CDT in AIMS) and Nantas Nardelli) developed the COMA method. In the paper, the researchers model the problem setting of StarCraft unit-management as a challenging cooperative multi-agent problem. The team’s training method outperforms existing methods and achieves high win rates against the StarCraft bot.

The team’s certificate will be presented at AAAI-18 on 6 February.

Article originally published on the Department of Computer Science website: on 17 January 2018.

Read More


Tim Seabrook and Adam Cobb will be taking up internships this year with NASA’s Frontier Development Lab (FDL).

NASA’s Frontier Development Lab (FDL) is an applied planetary science and machine learning research accelerator being run for its 2nd year, this Summer in Silicon Valley. combines machine learning experts and planetary scientists to address knowledge gaps in NASA’s Space programme.

Read More

Mobile Robotics Week

Oxford’s AIMS (Autonomous Intelligent Machines and Systems) CDT students joined MRG to take part in a robotics challenge, working with 2nd and 3rd year DPhil students to programme a self-driving robot.

In the final challenge each robot had to work its way around obstacles to reach a goal.


winning team

Winning Team

17103320_10155882498522926_58634399340946587_n 17155165_10155882498407926_3217047497768630764_n 17155268_10155882498222926_8562133422101161307_n(1) 17155268_10155882498222926_8562133422101161307_n 17155402_10155882529242926_2555575524867005803_n 17190901_10155882500972926_6990403480733768477_n(1) 17190901_10155882500972926_6990403480733768477_n 17200920_10155882497667926_9110357155352654902_n 17201194_10155882497762926_3852778438691702838_n 17201246_10155882497642926_7946312694864965524_n 17201326_10155882500557926_2676278119198119128_n 17203051_10155882498302926_598314311404096962_n

Read More

MRG at the Shell ECO Marathon

The Mobile Robotics Group took part in the Shell ECPO Marathon at the Queen Elizabeth Olympic Park

This was an amazing event, as well as getting to ride in the sutonomous car myself, we also had the pleasure of Kimi Kaikkonen driving!


2016-06-30 13.52.26 HDR 2016-06-30 13.52.26 2016-06-30 13.54.02 2016-06-30 13.55.47 2016-06-30 16.16.11 2016-06-30 16.16.12 2016-06-30 16.16.20 2016-06-30 16.37.54 2016-06-30 16.38.19-1 2016-06-30 16.38.25 2016-06-30 16.38.36 2016-06-30 16.39.07 2016-06-30 16.48.49

Read More