Goto

Collaborating Authors

 ijcai2023


#IJCAI2023 distinguished paper – Safe reinforcement learning via probabilistic logic shields

AIHub

Image created by author using DALL.E. Are you excited about self-driving cars? Would you trust autonomous driving technology if you were invited to step into a self-driving vehicle? Most importantly, how do you know whether you would be safe during the journey? Safety is difficult to measure, unlike accuracy, which we are more familiar with.


#IJCAI2023 in tweets: part 2

AIHub

The 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023) has now drawn to a close. The event, which took place in Macao from 19-25 August 2023, brought together AI researchers from across the globe. We've collected some tweets to give a flavour of what the participants got up to during the second half of the conference. You can see part 1 here. It was an honor presenting my poster today @ #IJCAI2023 https://t.co/iELd3RrzM3


Congratulations to the winners of the the #IJCAI2023 distinguished paper awards

AIHub

The IJCAI distinguished paper awards recognise some of the best papers presented at the conference each year. This year, three articles were named as distinguished papers. Abstract: Levin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansions before reaching a goal node, depending on the quality of the policy. This guarantee can be used as a loss function, which we call the LTS loss, to optimize neural networks representing the policy (LTS NN). In this work we show that the neural network can be substituted with parameterized context models originating from the online compression literature (LTS CM). We show that the LTS loss is convex under this new model, which allows for using standard convex optimization tools, and obtain convergence guarantees to the optimal parameters in an online setting for a given set of solution trajectories -- guarantees that cannot be provided for neural networks.


#IJCAI2023 in tweets: part 1

AIHub

The 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023) is taking place in Macao from 19-25 August 2023. The programme includes plenary talks, workshops, symposia and tutorials. We take a look at what participants have been getting up to during the first few days of the conference. The proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence #IJCAI2023 have just been published. Edited by Edith Elkind @UniofOxford Kudos to all the brilliant minds who contributed!

  Country: Asia > Macao (0.26)

What's on the programme at #IJCAI2023?

AIHub

The 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023) will take place in Macao from 19-25 August 2023. The programme includes plenary talks, workshops, symposia and tutorials. In addition to the main track, there are two special tracks, namely AI for good, and AI, the arts and creativity. There will be nine invited plenary talks at the conference this year. The 27 tutorials taking place at this year's event are:

  Country: Asia > Macao (0.35)