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

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.

And the winners are…

Levin Tree Search with Context Models
Laurent Orseau, Marcus Hutter, Levi H. S. Lelis

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. The new LTS+CM algorithm compares favorably against LTS+NN on several benchmarks: Sokoban (Boxoban), The Witness, and the 24-Sliding Tile puzzle (STP). The difference is particularly large on STP, where LTS+NN fails to solve most of the test instances while LTS+CM solves each test instance in a fraction of a second. Furthermore, we show that LTS+CM is able to learn a policy that solves the Rubik’s cube in only a few hundred expansions, which considerably improves upon previous machine learning techniques.

Read the paper in full here.

SAT-Based PAC Learning of Description Logic Concepts
Balder ten Cate, Maurice Funk, Jean Christoph Jung, Carsten Lutz

Abstract: We propose bounded fitting as a scheme for learning description logic concepts in the presence of ontologies. A main advantage is that the resulting learning algorithms come with theoretical guarantees regarding their generalization to unseen examples in the sense of PAC learning. We prove that, in contrast, several other natural learning algorithms fail to provide such guarantees. As a further contribution, we present the system SPELL which efficiently implements bounded fitting for the description logic ELH^r based on a SAT solver, and compare its performance to a state-of-the-art learner.

Read the paper in full here.

Safe Reinforcement Learning via Probabilistic Logic Shields
Wen-Chi Yang, Giuseppe Marra, Gavin Rens, Luc De Raedt

Abstract: Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe actions. However, traditional shielding techniques are difficult to integrate with continuous, end-to-end deep RL methods. To this end, we introduce Probabilistic Logic Policy Gradient (PLPG). PLPG is a model-based Safe RL technique that uses probabilistic logic programming to model logical safety constraints as differentiable functions. Therefore, PLPG can be seamlessly applied to any policy gradient algorithm while still providing the same convergence guarantees. In our experiments, we show that PLPG learns safer and more rewarding policies compared to other state-of-the-art shielding techniques.

Read the paper in full here.

Lucy Smith , Managing Editor for AIhub.

Lucy Smith , Managing Editor for AIhub.