Language models are often said to face a symbol grounding problem. While some have argued the problem can be solved without resort to other modalities, many have speculated that grounded learning is more efficient. We explore this question in Othello, a simplified, rule-based world that offers a controlled and interpretable testbed for studying world understanding. Building on prior work, we introduce VISOTHELLO, a multi-modal model trained jointly on move sequences and board images. Using the Othello rule understanding task, we examine whether multi-modal learning provides advantages over text-only approaches. We further evaluate robustness under semantically irrelevant perturbations and analyze the consistency of cross-modal alignment. Our results suggest that multi-modal training not only improves performance and robustness but also promotes convergence toward shared internal representations across different model architectures.

Using Machine Learning for move sequence visualization and generation in climbing Thomas Rimbot, Martin Jaggi, Luis Barba - EPFL Abstract --In this work, we investigate the application of Machine Learning techniques to sport climbing. Expanding upon previous projects, we develop a visualization tool for move sequence evaluation on a given boulder . Then, we look into move sequence prediction from simple holds sequence information using three different Transformer models. While the results are not conclusive, they are a first step in this kind of approach and lay the ground for future work. I NTRODUCTION Applying Machine Learning techniques to competitive sport has been an increasing trend in the past few years. We can for example cite the case of car racing or hockey. In this project, we focus on bouldering, a form of rock climbing where athletes are tasked with overcoming a small natural or artificial feature (about 4m high), requiring both physical strengths and problem-solving skills.

Chess is not a game. Chess is a well-defined form of computation. You may not be able to work out the answers, but in theory, there must be a solution, a right procedure in any position---John von Neumann The advent of computer chess engines based, such as AlphaZero, LCZero and Stockfish 14 NNUE, provides us with the ability to study optimal play. AI chess algorithms are based on pattern matching, efficient search and data-centric methods rather than rules based. Together with an objective functions based on maximising the probability of winning, we can now see what optimal play and strategies look like. One caveat is the black-box nature of these algorithms and lack of insight into the features that are empirically learned from self play.

The idea of dynamic move chains has been described in a preceding paper [10]. Re-using an earlier piece of search allows the tree to be forward-pruned, which is known to be dangerous, because it can potentially remove new information that would only be realised through a more exhaustive search process. The justification is the integrity in the position and small changes between positions make it more likely that an earlier result still applies. Larger problems where exhaustive search is not possible would also like a method that can guess accurately. This paper has added to the forward-pruning technique by using 'move tables' that can act in the same way as Transposition Tables, but for moves not positions. They use an efficient memory structure and have put the design into the context of short or long-term memories. The long-term memory includes simply rote-learning of other players' games. The forward-pruning technique can also be fortified to help to remove some potential errors. Another idea is 'long branches'. This plays a short move sequence, before returning to a full search at the resulting leaf nodes. Therefore, with some configuration the dynamic tables can be reliably used and relatively independently of the position. This has advanced some of the future work theory of the earlier paper, and made more explicit where logical plans and more knowledge-based approaches might be applied. The author would argue that the process is a very human approach to searching for chess moves.

Move pruning is a low-overhead technique for reducing the size of a depth first search tree. The existing algorithm for automatically discovering move pruning information is restricted to games where all moves can be applied to every state. This paper demonstrates an algorithm which handles a general class of single player games. It gives experimental results for our technique, demonstrating both the applicability to a range of games, and the reduction in search tree size. We also provide some conditions under which move pruning is safe, and when it may interfere with other search reduction techniques.

The basic thesis put forth in this article is that a problem solver is essentially an interpreter that carries out computations implicit in the problem formulation. A good problem formulation gives rise to what is conventionally called a strong problem solver; poor formulations correspond to weak problem solvers. Knowledge-based systems are discussed in the context of this thesis. We also make observations about the relationship between search strategy and problem formulation.