Parkinson's disease is marked by altered and increased firing characteristics of pathological oscillations in the brain. In other words, it causes abnormal synchronous oscillations and suppression during neurological processing. In order to examine and regulate the synchronization and pathological oscillations in motor circuits, deep brain stimulators (DBS) are used. Although machine learning methods have been applied for the investigation of suppression, these models require large amounts of training data and computational power, both of which pose challenges to resource-constrained DBS. This research proposes a novel reinforcement learning (RL) framework for suppressing the synchronization in neuronal activity during episodes of neurological disorders with less power consumption. The proposed RL algorithm comprises an ensemble of a temporal representation of stimuli and a twin-delayed deep deterministic (TD3) policy gradient algorithm. We quantify the stability of the proposed framework to noise and reduced synchrony using RL for three pathological signaling regimes: regular, chaotic, and bursting, and further eliminate the undesirable oscillations. Furthermore, metrics such as evaluation rewards, energy supplied to the ensemble, and the mean point of convergence were used and compared to other RL algorithms, specifically the Advantage actor critic (A2C), the Actor critic with Kronecker-featured trust region (ACKTR), and the Proximal policy optimization (PPO).

In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved tasks can allow agents to quickly solve new problems. In some cases, these new problems may be approximately solved by composing the solutions of previously solved primitive tasks (task composition). Otherwise, prior knowledge can be used to adjust the reward function for a new problem, in a way that leaves the optimal policy unchanged but enables quicker learning (reward shaping). In this work, we develop a general framework for reward shaping and task composition in entropy-regularized RL. To do so, we derive an exact relation connecting the optimal soft value functions for two entropy-regularized RL problems with different reward functions and dynamics. We show how the derived relation leads to a general result for reward shaping in entropy-regularized RL. We then generalize this approach to derive an exact relation connecting optimal value functions for the composition of multiple tasks in entropy-regularized RL. We validate these theoretical contributions with experiments showing that reward shaping and task composition lead to faster learning in various settings.

We present a novel hybrid learning method, HyLEAR, for solving the collision-free navigation problem for self-driving cars in POMDPs. HyLEAR leverages interposed learning to embed knowledge of a hybrid planner into a deep reinforcement learner to faster determine safe and comfortable driving policies. In particular, the hybrid planner combines pedestrian path prediction and risk-aware path planning with driving-behavior rule-based reasoning such that the driving policies also take into account, whenever possible, the ride comfort and a given set of driving-behavior rules. Our experimental performance analysis over the CARLA-CTS1 benchmark of critical traffic scenarios revealed that HyLEAR can significantly outperform the selected baselines in terms of safety and ride comfort.

Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies. This distribution of tasks can be specified by the curriculum. A curriculum is meant to improve the results of learning and accelerate it. We introduce Success Induced Task Prioritization (SITP), a framework for automatic curriculum learning, where a task sequence is created based on the success rate of each task. In this setting, each task is an algorithmically created environment instance with a unique configuration. The algorithm selects the order of tasks that provide the fastest learning for agents. The probability of selecting any of the tasks for the next stage of learning is determined by evaluating its performance score in previous stages. Experiments were carried out in the Partially Observable Grid Environment for Multiple Agents (POGEMA) and Procgen benchmark. We demonstrate that SITP matches or surpasses the results of other curriculum design methods. Our method can be implemented with handful of minor modifications to any standard RL framework and provides useful prioritization with minimal computational overhead.

Learning efficient and interpretable policies has been a challenging task in reinforcement learning (RL), particularly in the visual RL setting with complex scenes. While neural networks have achieved competitive performance, the resulting policies are often over-parameterized black boxes that are difficult to interpret and deploy efficiently. More recent symbolic RL frameworks have shown that high-level domain-specific programming logic can be designed to handle both policy learning and symbolic planning. However, these approaches rely on coded primitives with little feature learning, and when applied to high-dimensional visual scenes, they can suffer from scalability issues and perform poorly when images have complex object interactions. To address these challenges, we propose \textit{Differentiable Symbolic Expression Search} (DiffSES), a novel symbolic learning approach that discovers discrete symbolic policies using partially differentiable optimization. By using object-level abstractions instead of raw pixel-level inputs, DiffSES is able to leverage the simplicity and scalability advantages of symbolic expressions, while also incorporating the strengths of neural networks for feature learning and optimization. Our experiments demonstrate that DiffSES is able to generate symbolic policies that are simpler and more and scalable than state-of-the-art symbolic RL methods, with a reduced amount of symbolic prior knowledge.

Cybercriminals are moving towards zero-day attacks affecting resource-constrained devices such as single-board computers (SBC). Assuming that perfect security is unrealistic, Moving Target Defense (MTD) is a promising approach to mitigate attacks by dynamically altering target attack surfaces. Still, selecting suitable MTD techniques for zero-day attacks is an open challenge. Reinforcement Learning (RL) could be an effective approach to optimize the MTD selection through trial and error, but the literature fails when i) evaluating the performance of RL and MTD solutions in real-world scenarios, ii) studying whether behavioral fingerprinting is suitable for representing SBC's states, and iii) calculating the consumption of resources in SBC. To improve these limitations, the work at hand proposes an online RL-based framework to learn the correct MTD mechanisms mitigating heterogeneous zero-day attacks in SBC. The framework considers behavioral fingerprinting to represent SBCs' states and RL to learn MTD techniques that mitigate each malicious state. It has been deployed on a real IoT crowdsensing scenario with a Raspberry Pi acting as a spectrum sensor. More in detail, the Raspberry Pi has been infected with different samples of command and control malware, rootkits, and ransomware to later select between four existing MTD techniques. A set of experiments demonstrated the suitability of the framework to learn proper MTD techniques mitigating all attacks (except a harmfulness rootkit) while consuming <1 MB of storage and utilizing <55% CPU and <80% RAM.

The performance of an algorithm often critically depends on its parameter configuration. While a variety of automated algorithm configuration methods have been proposed to relieve users from the tedious and error-prone task of manually tuning parameters, there is still a lot of untapped potential as the learned configuration is static, i.e., parameter settings remain fixed throughout the run. However, it has been shown that some algorithm parameters are best adjusted dynamically during execution. Thus far, this is most commonly achieved through hand-crafted heuristics. A promising recent alternative is to automatically learn such dynamic parameter adaptation policies from data. In this article, we give the first comprehensive account of this new field of automated dynamic algorithm configuration (DAC), present a series of recent advances, and provide a solid foundation for future research in this field. Specifically, we (i) situate DAC in the broader historical context of AI research; (ii) formalize DAC as a computational problem; (iii) identify the methods used in prior art to tackle this problem; and (iv) conduct empirical case studies for using DAC in evolutionary optimization, AI planning, and machine learning.

Learning from the interaction is the primary way biological agents know about the environment and themselves. Modern deep reinforcement learning (DRL) explores a computational approach to learning from interaction and has significantly progressed in solving various tasks. However, the powerful DRL is still far from biological agents in energy efficiency. Although the underlying mechanisms are not fully understood, we believe that the integration of spiking communication between neurons and biologically-plausible synaptic plasticity plays a prominent role. Following this biological intuition, we optimize a spiking policy network (SPN) by a genetic algorithm as an energy-efficient alternative to DRL. Our SPN mimics the sensorimotor neuron pathway of insects and communicates through event-based spikes. Inspired by biological research that the brain forms memories by forming new synaptic connections and rewires these connections based on new experiences, we tune the synaptic connections instead of weights in SPN to solve given tasks. Experimental results on several robotic control tasks show that our method can achieve the performance level of mainstream DRL methods and exhibit significantly higher energy efficiency.

In this paper, we present a framework for learning quadruped navigation by integrating central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework. Through both exteroceptive and proprioceptive sensing, the agent learns to modulate the intrinsic oscillator setpoints (amplitude and frequency) and coordinate rhythmic behavior among different oscillators to track velocity commands while avoiding collisions with the environment. We compare different neural network architectures (i.e. memory-free and memory-enabled) which learn implicit interoscillator couplings, as well as varying the strength of the explicit coupling weights in the oscillator dynamics equations. We train our policies in simulation and perform a sim-to-real transfer to the Unitree Go1 quadruped, where we observe robust navigation in a variety of scenarios. Our results show that both memory-enabled policy representations and explicit interoscillator couplings are beneficial for a successful sim-to-real transfer for navigation tasks. Video results can be found at https://youtu.be/O_LX1oLZOe0.

Advances in reinforcement learning have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most theoretical work pertains to finite state and action spaces. We propose building a theoretical understanding of continuous state and action spaces by employing a geometric lens. Central to our work is the idea that the transition dynamics induce a low dimensional manifold of reachable states embedded in the high-dimensional nominal state space. We prove that, under certain conditions, the dimensionality of this manifold is at most the dimensionality of the action space plus one. This is the first result of its kind, linking the geometry of the state space to the dimensionality of the action space. We empirically corroborate this upper bound for four MuJoCo environments. We further demonstrate the applicability of our result by learning a policy in this low dimensional representation. To do so we introduce an algorithm that learns a mapping to a low dimensional representation, as a narrow hidden layer of a deep neural network, in tandem with the policy using DDPG. Our experiments show that a policy learnt this way perform on par or better for four MuJoCo control suite tasks.