No-Reward Meta Learning (NoRML)
Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback for adaptation. However, in many scenarios this reward signal might not be readily available for the target task, or the difference between the environments can be implicit and only observable from the dynamics. To this end, we introduce a method that allows for self-adaptation of learned policies: No-Reward Meta Learning (NoRML). NoRML extends Model Agnostic Meta Learning (MAML) for RL and uses observable dynamics of the environment instead of an explicit reward function in MAML’s finetune step. Our method has a more expressive update step than MAML, while maintaining MAML’s gradient based foundation. Additionally, in order to allow more targeted exploration, we implement an extension to MAML that effectively disconnects the meta-policy parameters from the fine-tuned policies’ parameters. We first study our method on a number of synthetic control problems and then validate our method on common benchmark environments, showing that NoRML outperforms MAML when the dynamics change between tasks. …

CROSSBOW
Deep learning models are trained on servers with many GPUs, and training must scale with the number of GPUs. Systems such as TensorFlow and Caffe2 train models with parallel synchronous stochastic gradient descent: they process a batch of training data at a time, partitioned across GPUs, and average the resulting partial gradients to obtain an updated global model. To fully utilise all GPUs, systems must increase the batch size, which hinders statistical efficiency. Users tune hyper-parameters such as the learning rate to compensate for this, which is complex and model-specific. We describe CROSSBOW, a new single-server multi-GPU system for training deep learning models that enables users to freely choose their preferred batch size – however small – while scaling to multiple GPUs. CROSSBOW uses many parallel model replicas and avoids reduced statistical efficiency through a new synchronous training method. We introduce SMA, a synchronous variant of model averaging in which replicas independently explore the solution space with gradient descent, but adjust their search synchronously based on the trajectory of a globally-consistent average model. CROSSBOW achieves high hardware efficiency with small batch sizes by potentially training multiple model replicas per GPU, automatically tuning the number of replicas to maximise throughput. Our experiments show that CROSSBOW improves the training time of deep learning models on an 8-GPU server by 1.3-4x compared to TensorFlow. …

Knowledge Compilation
Knowledge compilation is a family of approaches for addressing the intractability of a number of artificial intelligence problems. A propositional model is compiled in an off-line phase in order to support some queries in polytime. Many ways of compiling a propositional models exist. Among others: NNF, DNNF, d-DNNF, BDD, SDD, MDD, DNF and CNF. Different compiled representations have different properties. The three main properties are:
• The compactness of the representation
• The queries that are supported in polytime
• The transformations of the representations that can be performed in polytime …

Block-Wise Network Generation Pipeline (BlockQNN)
Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained to choose component layers sequentially. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2.35% top-1 error rate on CIFAR-10. (2) it offers tremendous reduction of the search space in designing networks, spending only 3 days with 32 GPUs. A faster version can yield a comparable result with only 1 GPU in 20 hours. (3) it has strong generalizability in that the network built on CIFAR also performs well on the larger-scale dataset. The best network achieves very competitive accuracy of 82.0% top-1 and 96.0% top-5 on ImageNet. …