Learning Graphical Models
Model Interpretability through the Lens of Computational Complexity Pablo Barceló
W e only accept 1 out of 20 papers that do not cite any other paper from our own journal.
Dynamic Bottleneck for Robust Self-Supervised Exploration
However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dynamics-irrelevant information, we propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle.
Scalable Online Planning via Reinforcement Learning Fine-Tuning
Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many other settings, are tabular. Tabular search methods do not scale well with the size of the search space, and this problem is exacerbated by stochasticity and partial observability. In this work we replace tabular search with online model-based fine-tuning of a policy neural network via reinforcement learning, and show that this approach outperforms state-of-the-art search algorithms in benchmark settings. In particular, we use our search algorithm to achieve a new state-of-the-art result in self-play Hanabi, and show the generality of our algorithm by also showing that it outperforms tabular search in the Atari game Ms. Pacman.
Deep Rao-Blackwellised Particle Filters for Time Series Forecasting
However, most systems of practical interest are non-linear, requiring more complex models. Many approximate inference methods have been developed for non-linear dynamical systems: Deterministic methods approximate the filtering and smoothing distributions e.g. by using a Taylor series
Graph Differentiable Architecture Search with Structure Learning
Proof A.1 W e firstly give Lemma 1: Lemma 1 The operation weights are caculated by a softmax function. The number of target node's intra-group neighbors is "S" indicates the setting of searching phase. "E" indicates the setting of evaluation phase. The hyper-parameter λ which controls the hidden feature smoothness is set to be 0 .125 . We show the variance of synthetic graph experiment in Table 1 to endorse our analysis in Section 3. The table shows that the variance of accuracy is relatively big in the experiment setting. However, all the results are average of 100 runs.
