The capability of imagining internally with a mental model of the world is vitally important for human cognition. If a machine intelligent agent can learn a world model to create a "dream" environment, it can then internally ask what-if questions -- simulate the alternative futures that haven't been experienced in the past yet -- and make optimal decisions accordingly. Existing world models are established typically by learning spatio-temporal regularities embedded from the past sensory signal without taking into account confounding factors that influence state transition dynamics. As such, they fail to answer the critical counterfactual questions about "what would have happened" if a certain action policy was taken. In this paper, we propose Causal World Models (CWMs) that allow unsupervised modeling of relationships between the intervened observations and the alternative futures by learning an estimator of the latent confounding factors. We empirically evaluate our method and demonstrate its effectiveness in a variety of physical reasoning environments. Specifically, we show reductions in sample complexity for reinforcement learning tasks and improvements in counterfactual physical reasoning.

While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is also known as the aleatoric uncertainty and is closely related to the notion of risk. In this work, we make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. In particular, we focus on a variance-constrained policy optimization problem where the goal is to find a policy that maximizes the expected value of the long-run average reward, subject to a constraint that the long-run variance of the average reward is upper bounded by a threshold. Utilizing Lagrangian and Fenchel dualities, we transform the original problem into an unconstrained saddle-point policy optimization problem, and propose an actor-critic algorithm that iteratively and efficiently updates the policy, the Lagrange multiplier, and the Fenchel dual variable. When both the value and policy functions are represented by multi-layer overparameterized neural networks, we prove that our actor-critic algorithm generates a sequence of policies that finds a globally optimal policy at a sublinear rate.

Portfolio optimization is one of the most attentive fields that have been researched with machine learning approaches. Many researchers attempted to solve this problem using deep reinforcement learning due to its efficient inherence that can handle the property of financial markets. However, most of them can hardly be applicable to real-world trading since they ignore or extremely simplify the realistic constraints of transaction costs. These constraints have a significantly negative impact on portfolio profitability. In our research, a conservative level of transaction fees and slippage are considered for the realistic experiment. To enhance the performance under those constraints, we propose a novel Deterministic Policy Gradient with 2D Relative-attentional Gated Transformer (DPGRGT) model. Applying learnable relative positional embeddings for the time and assets axes, the model better understands the peculiar structure of the financial data in the portfolio optimization domain. Also, gating layers and layer reordering are employed for stable convergence of Transformers in reinforcement learning. In our experiment using U.S. stock market data of 20 years, our model outperformed baseline models and demonstrated its effectiveness.

Dialogue policy learning based on reinforcement learning is difficult to be applied to real users to train dialogue agents from scratch because of the high cost. User simulators, which choose random user goals for the dialogue agent to train on, have been considered as an affordable substitute for real users. However, this random sampling method ignores the law of human learning, making the learned dialogue policy inefficient and unstable. We propose a novel framework, Automatic Curriculum Learning-based Deep Q-Network (ACL-DQN), which replaces the traditional random sampling method with a teacher policy model to realize the dialogue policy for automatic curriculum learning. The teacher model arranges a meaningful ordered curriculum and automatically adjusts it by monitoring the learning progress of the dialogue agent and the over-repetition penalty without any requirement of prior knowledge. The learning progress of the dialogue agent reflects the relationship between the dialogue agent's ability and the sampled goals' difficulty for sample efficiency. The over-repetition penalty guarantees the sampled diversity. Experiments show that the ACL-DQN significantly improves the effectiveness and stability of dialogue tasks with a statistically significant margin. Furthermore, the framework can be further improved by equipping with different curriculum schedules, which demonstrates that the framework has strong generalizability.

In this article, two types of methods from different perspectives based on spectral normalization are described for ensuring the stability of the system controlled by a neural network. The first one is that the L2 gain of the feedback system is bounded less than 1 to satisfy the stability condition derived from the small-gain theorem. While explicitly including the stability condition, the first method may provide an insufficient performance on the neural network controller due to its strict stability condition. To overcome this difficulty, the second one is proposed, which improves the performance while ensuring the local stability with a larger region of attraction. In the second method, the stability is ensured by solving linear matrix inequalities after training the neural network controller. The spectral normalization proposed in this article improves the feasibility of the a-posteriori stability test by constructing tighter local sectors. The numerical experiments show that the second method provides enough performance compared with the first one while ensuring enough stability compared with the existing reinforcement learning algorithms.

The sample-inefficiency problem in Artificial Intelligence refers to the inability of current Deep Reinforcement Learning models to optimize action policies within a small number of episodes. Recent studies have tried to overcome this limitation by adding memory systems and architectural biases to improve learning speed, such as in Episodic Reinforcement Learning. However, despite achieving incremental improvements, their performance is still not comparable to how humans learn behavioral policies. In this paper, we capitalize on the design principles of the Distributed Adaptive Control (DAC) theory of mind and brain to build a novel cognitive architecture (DAC-ML) that, by incorporating a hippocampus-inspired sequential memory system, can rapidly converge to effective action policies that maximize reward acquisition in a challenging foraging task.

In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a natural fit for studying continual learning. We then provide a taxonomy of different continual RL formulations and mathematically characterize the non-stationary dynamics of each setting. We go on to discuss evaluation of continual RL agents, providing an overview of benchmarks used in the literature and important metrics for understanding agent performance. Finally, we highlight open problems and challenges in bridging the gap between the current state of continual RL and findings in neuroscience. While still in its early days, the study of continual RL has the promise to develop better incremental reinforcement learners that can function in increasingly realistic applications where non-stationarity plays a vital role. These include applications such as those in the fields of healthcare, education, logistics, and robotics.

Online reviews are a vital source of information when purchasing a service or a product. Opinion spammers manipulate these reviews, deliberately altering the overall perception of the service. Though there exists a corpus of online reviews, only a few have been labeled as spam or non-spam, making it difficult to train spam detection models. We propose an adversarial training mechanism leveraging the capabilities of Generative Pre-Training 2 (GPT-2) for classifying opinion spam with limited labeled data and a large set of unlabeled data. Experiments on TripAdvisor and YelpZip datasets show that the proposed model outperforms state-of-the-art techniques by at least 7% in terms of accuracy when labeled data is limited. The proposed model can also generate synthetic spam/non-spam reviews with reasonable perplexity, thereby, providing additional labeled data during training.

Purpose: Lesion segmentation in medical imaging is key to evaluating treatment response. We have recently shown that reinforcement learning can be applied to radiological images for lesion localization. Furthermore, we demonstrated that reinforcement learning addresses important limitations of supervised deep learning; namely, it can eliminate the requirement for large amounts of annotated training data and can provide valuable intuition lacking in supervised approaches. However, we did not address the fundamental task of lesion/structure-of-interest segmentation. Here we introduce a method combining unsupervised deep learning clustering with reinforcement learning to segment brain lesions on MRI. Materials and Methods: We initially clustered images using unsupervised deep learning clustering to generate candidate lesion masks for each MRI image. The user then selected the best mask for each of 10 training images. We then trained a reinforcement learning algorithm to select the masks. We tested the corresponding trained deep Q network on a separate testing set of 10 images. For comparison, we also trained and tested a U-net supervised deep learning network on the same set of training/testing images. Results: Whereas the supervised approach quickly overfit the training data and predictably performed poorly on the testing set (16% average Dice score), the unsupervised deep clustering and reinforcement learning achieved an average Dice score of 83%. Conclusion: We have demonstrated a proof-of-principle application of unsupervised deep clustering and reinforcement learning to segment brain tumors. The approach represents human-allied AI that requires minimal input from the radiologist without the need for hand-traced annotation.

Over the last decade, the long-running endeavour to automate high-level processes in machine learning (ML) has risen to mainstream prominence, stimulated by advances in optimisation techniques and their impact on selecting ML models/algorithms. Central to this drive is the appeal of engineering a computational system that both discovers and deploys high-performance solutions to arbitrary ML problems with minimal human interaction. Beyond this, an even loftier goal is the pursuit of autonomy, which describes the capability of the system to independently adjust an ML solution over a lifetime of changing contexts. However, these ambitions are unlikely to be achieved in a robust manner without the broader synthesis of various mechanisms and theoretical frameworks, which, at the present time, remain scattered across numerous research threads. Accordingly, this review seeks to motivate a more expansive perspective on what constitutes an automated/autonomous ML system, alongside consideration of how best to consolidate those elements. In doing so, we survey developments in the following research areas: hyperparameter optimisation, multi-component models, neural architecture search, automated feature engineering, meta-learning, multi-level ensembling, dynamic adaptation, multi-objective evaluation, resource constraints, flexible user involvement, and the principles of generalisation. We also develop a conceptual framework throughout the review, augmented by each topic, to illustrate one possible way of fusing high-level mechanisms into an autonomous ML system. Ultimately, we conclude that the notion of architectural integration deserves more discussion, without which the field of automated ML risks stifling both its technical advantages and general uptake.