Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its inference path until it reaches a target. However, in an incomplete KG environment, the agent receives low-quality rewards corrupted by false negatives in the training data, which harms generalization at test time. Furthermore, since no golden action sequence is used for training, the agent can be misled by spurious search trajectories that incidentally lead to the correct answer. We propose two modeling advances to address both issues: (1) we reduce the impact of false negative supervision by adopting a pretrained one-hop embedding model to estimate the reward of unobserved facts; (2) we counter the sensitivity to spurious paths of on-policy RL by forcing the agent to explore a diverse set of paths using randomly generated edge masks. Our approach significantly improves over existing path-based KGQA models on several benchmark datasets and is comparable or better than embedding-based models.

We introduce a new virtual environment for simulating a card game known as "Big 2". This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many current reinforcement learning methods. We then use the recently proposed "Proximal Policy Optimization" algorithm to train a deep neural network to play the game, purely learning via self-play, and find that it is able to reach a level which outperforms amateur human players after only a relatively short amount of training time and without needing to search a tree of future game states.

The current state of the art in playing many important perfect information games, including Chess and Go, combines planning and deep reinforcement learning with self-play. We extend this approach to imperfect information games and present ExIt-OOS, a novel approach to playing imperfect information games within the Expert Iteration framework and inspired by AlphaZero. We use Online Outcome Sampling, an online search algorithm for imperfect information games in place of MCTS. While training online, our neural strategy is used to improve the accuracy of playouts in OOS, allowing a learning and planning feedback loop for imperfect information games.

If you are as fascinated by Deep Q-Learning as I am but never had the time to understand or implement it, this is for you: In one Jupyter notebook I will 1) briefly explain how Reinforcement Learning differs from Supervised Learning, 2) discuss the theory behind Deep Q-Networks (DQN) by telling you where you find the respective explanations in the papers and what they mean and 3) how to implement the components needed to make it work in python and tensorflow. In 2013 a London based startup called DeepMind published a groundbreaking paper called Playing Atari with Deep Reinforcement Learning on arXiv: The authors presented a variant of Reinforcement Learning called Deep Q-Learning that is able to successfully learn control policies for different Atari 2600 games receiving only screen pixels as input and a reward when the game score changes. This is an astonishing result because previously "AIs" used to be limited to one single game, for instance, chess, whereas in this case the types and contents of the games in the Arcade Learning Environment vary significantly and yet no adjustment of the architecture, learning algorithm or hyperparameters is needed. No wonder DeepMind was bought by Google for 500 Million Dollars. The company has since been one of the leading institutions advancing Deep Learning research and a later article discussing DQN has been published in Nature.

Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.

Search-oriented conversational systems rely on information needs expressed in natural language (NL). We focus here on the understanding of NL expressions for building keyword-based queries. We propose a reinforcement-learning-driven translation model framework able to 1) learn the translation from NL expressions to queries in a supervised way, and, 2) to overcome the lack of large-scale dataset by framing the translation model as a word selection approach and injecting relevance feedback in the learning process. Experiments are carried out on two TREC datasets and outline the effectiveness of our approach.

Abstract--In this paper, we implement two state-of-art continuous reinforcement learning algorithms, Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO) in portfolio management. Both of them are widely-used in game playing and robot control. What's more, PPO has appealing theoretical propeties which is hopefully potential in portfolio management. We present the performances of them under different settings, including different learning rate, objective function, markets, feature combinations, in order to provide insights for parameter tuning, features selection and data preparation. Utilizing deep reinforcement learning in portfolio management is gaining popularity in the area of algorithmic trading. However, deep learning is notorious for its sensitivity to neural network structure, feature engineering and so on. Therefore, in our experiments, we explored influences of different optimizers and network structures on trading agents utilizing two kinds of deep reinforcement learning algorithms, deep deterministic policy gradient (DDPG) and proximal policy optimization (PPO). Our experiments were conveyed on datasets of China and America stock market.

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS and DPP-Net. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.

We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users' preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforcement learning techniques in order to reduce the sample complexity. Both simulation and real-user experiments suggest that our method significantly advances the state of the art. Our source code is freely available at https://github.com/UKPLab/

Although exploration in reinforcement learning is well understood from a theoretical point of view, provably correct methods remain impractical. In this paper we study the interplay between exploration and approximation, what we call \emph{approximate exploration}. We first provide results when the approximation is explicit, quantifying the performance of an exploration algorithm, MBIE-EB \citep{strehl2008analysis}, when combined with state aggregation. In particular, we show that this allows the agent to trade off between learning speed and quality of the policy learned. We then turn to a successful exploration scheme in practical, pseudo-count based exploration bonuses \citep{bellemare2016unifying}. We show that choosing a density model implicitly defines an abstraction and that the pseudo-count bonus incentivizes the agent to explore using this abstraction. We find, however, that implicit exploration may result in a mismatch between the approximated value function and exploration bonus, leading to either under- or over-exploration.