Cognitive science aims to identify the principles and mechanisms that underlie adaptive behavior. An important part of this endeavor is the development of unifying, normative theories that specify "design principles" that guide or constrain how intelligent systems respond to their environment [Marr, 1982, Anderson, 1990, Lewis et al., 2014, Griffiths et al., 2015, Gershman et al., 2015]. For example, accounts of learning, cognition, and decision-making often posit a function that an organism is optimizing--e.g., maximizing long-term reward or minimizing prediction error--and test plausible algorithms that achieve this--e.g., a particular learning rule or inference process. Historically, normative theories in cognitive science have been developed in tandem with new formal approaches in computer science and statistics. This partnership has been fruitful even given differences in scientific goals (e.g., engineering artificial intelligence versus reverse-engineering biological intelligence). Normative theories play a key role in facilitating cross-talk between different disciplines by providing a shared set of mathematical, analytical, and conceptual tools for describing computational problems and how to solve them [Ho and Griffiths, 2022]. This paper is written in the spirit of such cross-disciplinary fertilization. Here, we review recent work in computer science [Arumugam and Van Roy, 2021a, 2022] that develops a novel approach for unifying three distinct mathematical frameworks that will be familiar to many cognitive scientists (Figure 1).

Model-based approaches to reinforcement learning (MBRL) exhibit favorable performance in practice, but their theoretical guarantees in large spaces are mostly restricted to the setting when transition model is Gaussian or Lipschitz, and demands a posterior estimate whose representational complexity grows unbounded with time. In this work, we develop a novel MBRL method (i) which relaxes the assumptions on the target transition model to belong to a generic family of mixture models; (ii) is applicable to large-scale training by incorporating a compression step such that the posterior estimate consists of a Bayesian coreset of only statistically significant past state-action pairs; and (iii) exhibits a sublinear Bayesian regret. To achieve these results, we adopt an approach based upon Stein's method, which, under a smoothness condition on the constructed posterior and target, allows distributional distance to be evaluated in closed form as the kernelized Stein discrepancy (KSD). The aforementioned compression step is then computed in terms of greedily retaining only those samples which are more than a certain KSD away from the previous model estimate. Experimentally, we observe that this approach is competitive with several state-of-the-art RL methodologies, and can achieve up-to 50 percent reduction in wall clock time in some continuous control environments.

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments have implicit constraints that are difficult to specify and transfer to a learning agent. To address this challenge, we propose a novel method that utilizes the principle of maximum causal entropy to learn constraints and an optimal policy that adheres to these constraints, using demonstrations of agents that abide by the constraints. We prove convergence in a tabular setting and provide an approximation which scales to complex environments. We evaluate the effectiveness of the learned policy by assessing the reward received and the number of constraint violations, and we evaluate the learned cost function based on its transferability to other agents. Our method has been shown to outperform state-of-the-art approaches across a variety of tasks and environments, and it is able to handle problems with stochastic dynamics and a continuous state-action space.

Data augmentation is a widely used technique for improving model performance in machine learning, particularly in computer vision and natural language processing. Recently, there has been increasing interest in applying augmentation techniques to reinforcement learning (RL) problems, with a focus on image-based augmentation. In this paper, we explore a set of generic wrappers designed to augment RL environments with noise and encourage agent exploration and improve training data diversity which are applicable to a broad spectrum of RL algorithms and environments. Specifically, we concentrate on augmentations concerning states, rewards, and transition dynamics and introduce two novel augmentation techniques. In addition, we introduce a noise rate hyperparameter for control over the frequency of noise injection. We present experimental results on the impact of these wrappers on return using three popular RL algorithms, Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), and Proximal Policy Optimization (PPO), across five MuJoCo environments. To support the choice of augmentation technique in practice, we also present analysis that explores the performance these techniques across environments. Lastly, we publish the wrappers in our noisyenv repository for use with gym environments.

Graph neural networks (GNNs) have achieved remarkable success in various real-world applications. However, recent studies highlight the vulnerability of GNNs to malicious perturbations. Previous adversaries primarily focus on graph modifications or node injections to existing graphs, yielding promising results but with notable limitations. Graph modification attack~(GMA) requires manipulation of the original graph, which is often impractical, while graph injection attack~(GIA) necessitates training a surrogate model in the black-box setting, leading to significant performance degradation due to divergence between the surrogate architecture and the actual victim model. Furthermore, most methods concentrate on a single attack goal and lack a generalizable adversary to develop distinct attack strategies for diverse goals, thus limiting precise control over victim model behavior in real-world scenarios. To address these issues, we present a gradient-free generalizable adversary that injects a single malicious node to manipulate the classification result of a target node in the black-box evasion setting. We propose Gradient-free Generalizable Single Node Injection Attack, namely G$^2$-SNIA, a reinforcement learning framework employing Proximal Policy Optimization. By directly querying the victim model, G$^2$-SNIA learns patterns from exploration to achieve diverse attack goals with extremely limited attack budgets. Through comprehensive experiments over three acknowledged benchmark datasets and four prominent GNNs in the most challenging and realistic scenario, we demonstrate the superior performance of our proposed G$^2$-SNIA over the existing state-of-the-art baselines. Moreover, by comparing G$^2$-SNIA with multiple white-box evasion baselines, we confirm its capacity to generate solutions comparable to those of the best adversaries.

Most exploration research on reinforcement learning (RL) has paid attention to `the way of exploration', which is `how to explore'. The other exploration research, `when to explore', has not been the main focus of RL exploration research. The issue of `when' of a monolithic exploration in the usual RL exploration behaviour binds an exploratory action to an exploitational action of an agent. Recently, a non-monolithic exploration research has emerged to examine the mode-switching exploration behaviour of humans and animals. The ultimate purpose of our research is to enable an agent to decide when to explore or exploit autonomously. We describe the initial research of an autonomous multi-mode exploration of non-monolithic behaviour in an options framework. The higher performance of our method is shown against the existing non-monolithic exploration method through comparative experimental results.

Active flow control (AFC) involves manipulating fluid flow over time to achieve a desired performance or efficiency. AFC, as a sequential optimisation task, can benefit from utilising Reinforcement Learning (RL) for dynamic optimisation. In this work, we introduce Gym-preCICE, a Python adapter fully compliant with Gymnasium (formerly known as OpenAI Gym) API to facilitate designing and developing RL environments for single- and multi-physics AFC applications. In an actor-environment setting, Gym-preCICE takes advantage of preCICE, an open-source coupling library for partitioned multi-physics simulations, to handle information exchange between a controller (actor) and an AFC simulation environment. The developed framework results in a seamless non-invasive integration of realistic physics-based simulation toolboxes with RL algorithms. Gym-preCICE provides a framework for designing RL environments to model AFC tasks, as well as a playground for applying RL algorithms in various AFC-related engineering applications.

Offline reinforcement learning -- learning a policy from a batch of data -- is known to be hard for general MDPs. These results motivate the need to look at specific classes of MDPs where offline reinforcement learning might be feasible. In this work, we explore a restricted class of MDPs to obtain guarantees for offline reinforcement learning. The key property, which we call Action Impact Regularity (AIR), is that actions primarily impact a part of the state (an endogenous component) and have limited impact on the remaining part of the state (an exogenous component). AIR is a strong assumption, but it nonetheless holds in a number of real-world domains including financial markets. We discuss algorithms that exploit the AIR property, and provide a theoretical analysis for an algorithm based on Fitted-Q Iteration. Finally, we demonstrate that the algorithm outperforms existing offline reinforcement learning algorithms across different data collection policies in simulated and real world environments where the regularity holds.

Recent advancements in legged locomotion research have made legged robots a preferred choice for navigating challenging terrains when compared to their wheeled counterparts. This paper presents a novel locomotion policy, trained using Deep Reinforcement Learning, for a quadrupedal robot equipped with an additional prismatic joint between the knee and foot of each leg. The training is performed in NVIDIA Isaac Gym simulation environment. Our study investigates the impact of these joints on maintaining the quadruped's desired height and following commanded velocities while traversing challenging terrains. We provide comparison results, based on a Cost of Transport (CoT) metric, between quadrupeds with and without prismatic joints. The learned policy is evaluated on a set of challenging terrains using the CoT metric in simulation. Our results demonstrate that the added degrees of actuation offer the locomotion policy more flexibility to use the extra joints to traverse terrains that would be deemed infeasible or prohibitively expensive for the conventional quadrupedal design, resulting in significantly improved efficiency.

This paper aims to develop a new human-machine interface to improve the rehabilitation performance from the perspective of both the user (patient) and the machine (robot) by introducing the co-adaption techniques via model based reinforcement learning. Previous studies focus more on robot assistance, i.e., to improve the control strategy so as to fulfil the objective of Assist-As-Needed. In this study, we treat the full process of robot-assisted rehabilitation as a co-adaptive process or mutual learning process, and emphasize the adaptation of the user to the machine. To this end, we proposed a Co-adaptive MDPs (CaMDPs) model to quantify the learning rates based on cooperative multi-agent reinforce learning (MARL) in the high abstraction layer of the systems. We proposed several approaches to cooperatively adjust the Policy Improvement among the two agents in the framework of Policy Iteration. Based on the proposed co-adaptive MDPs, simulation study indicates the non-stationary problem can be mitigated by using various proposed Policy Improvement approaches.