2nd Applied Active Inference Symposium, part 2

[Music] hello and welcome everyone to the second applied active inference symposium hosted by the active inference institute it is july 31st 2022 and this is the first session of the symposium the focus of the symposium will be robotics and the presentations will be centered around that theme if you have ideas for future symposium topics and want to participate in organizing please reach out to us for those of you watching live please post questions in the chat and we will ask the presenters during the roundtable discussion this symposium will be recorded transcribed and archived for lasting access we will make the playlist available for asynchronous participation if you would like to participate in the transcription of the video please reach out to us at activeinference gmail.com we will have five presenters followed by a roundtable discussion the presenters in the first block are going to be tim schneider presenting active inference for robotic manipulation with co-authors let's see sorry oh i don't have any listed here um okay and then next let's see next is tim verbellen um and he is presenting robotics modeling the world from pixels using deep active inference also no co-authors listed and then next will be next will be ben white with artificial empathy active inference and collective intelligence and he has co-authors mark miller and daphne damascus demacos sorry if i got that wrong and after that we will have a talk by noor sajid learning agent preferences and let's see her are ah there she is oh she doesn't have any listed here either and then finally we have one hua chen with the talk called dual control for exploitation and exploration and its applications in robotic autonomous search and that's it so with pleasure i introduce tim schneider uh please take it away yeah thanks a lot for the introduction i'm just quickly going to share my screen i hope you can see that all right yeah so my name is tim schneider and today i want to talk about our work on active influence for robotic manipulation [Music] so i think we can all agree that manipulation so there's some noise on the background sorry yeah it never went i think we can all agree that uh manipulation is one of these central abilities that we need in our everyday life like be it cooking writing or using tools and you can obviously think of a variety of other tasks that also require dexterous manipulation however despite this significance of manipulation in our everyday lives robotic manipulation is still a largely unsolved topic and i think one of the main reasons for this is that usually in classic robotics how we did it for years we always assume that everything is kind of known that we know where everything is how everything behaves but in unstructured environments this is usually not the case and so what we need is very adaptive policies that are able to react to changes in the environment and are robust to to all kind of perturbations so what my lab focuses on or at least in part focuses on is applying reinforcement learning to robotic manipulation so learn these skills instead of programming them by hand however this is also not super straightforward in manipulation and one of the central challenges here is to to perform the exploration so in reinforcement learning we always have to explore a task before we can complete it like for example here in this task um this robot has to move up this little ball into a target zone on this tilted table and what we usually do and what is done here is that we just apply some random actions in the beginning and also throughout the the entire optimization procedure and we just hope that this will give us some useful insight into how the world actually behaves and how we can create a high reward in these settings but i think in manipulation this is usually not the case because if we just apply random noise we end up dropping the objects we are trying to manipulate we end up maybe destroying even parts of the environment so…