OxTalks is Changing
On 28th November OxTalks will move to the new Halo platform and will become 'Oxford Events' (full details are available on the Staff Gateway).
There will be an OxTalks freeze beginning on Friday 14th November. This means you will need to publish any of your known events to OxTalks by then as there will be no facility to publish or edit events in that fortnight. During the freeze, all events will be migrated to the new Oxford Events site. It will still be possible to view events on OxTalks during this time.
If you have any questions, please contact halo@digital.ox.ac.uk
Opponent-Shaping and Interference in General-Sum Games
In general-sum games, the interaction of self-interested learning agents commonly leads to collectively worst-case outcomes, such as defect-defect in the iterated prisoner’s dilemma (IPD). To overcome this, some methods, such as Learning with Opponent-Learning Awareness (LOLA), shape their opponents’ learning process. However, these methods are myopic since only a small number of steps can be anticipated, are asymmetric since they treat other agents as naïve learners, and require the use of higher-order derivatives, which are calculated through white-box access to an opponent’s differentiable learning algorithm.
In this talk I will first introduce Model-Free Opponent Shaping (M-FOS), which overcomes all of these limitations. M-FOS learns in a meta-game in which each meta-step is an episode of the underlying (``inner’‘) game. The meta-state consists of the inner policies, and the meta-policy produces a new inner policy to be used in the next episode. M-FOS then uses generic model-free optimisation methods to learn meta-policies that accomplish long-horizon opponent shaping.
I will finish off the talk with our recent results for adversarial (or cooperative) cheap-talk: How can agents interfere with (or support) the learning process of other agents without being able to act in the environment?
Date:
7 February 2024, 12:30
Venue:
Please register to receive venue details
Speaker:
Professor Jakob Foerster (Engineering Science, Oxford)
Host:
Dr Caroline Green (Oxford)
Part of:
Ethics in AI Lunchtime Seminars
Booking required?:
Required
Booking url:
https://www.oxford-aiethics.ox.ac.uk/ethics-ai-lunchtime-seminars-opponent-shaping-and-interference-general-sum-games
Booking email:
aiethics@philosophy.ox.ac.uk
Cost:
Free
Audience:
Public
Editors:
Marie Watson,
Lauren Czerniawska
