Recent work has discovered that deep reinforcement learning (DRL) policies are vulnerable to adversarial examples. These attacks mislead the policy of DRL agents by perturbing the state of the environment observed by agents. They are feasible in principle but too slow to fool DRL policies in real time. We propose a new attack to fool DRL policies that is both effective and efficient enough to be mounted in real time. We utilize the Universal Adversarial Perturbation (UAP) method to compute effective perturbations independent of the individual inputs to which they are applied. Via an extensive evaluation using Atari 2600 games, we show that our technique is effective, as it fully degrades the performance of both deterministic and stochastic policies (up to 100%, even when the $l_\infty$ bound on the perturbation is as small as 0.005). We also show that our attack is efficient, incurring an online computational cost of 0.027ms on average. It is faster compared to the response time (0.6ms on average) of agents with different DRL policies, and considerably faster than prior attacks (2.7ms on average). Furthermore, we demonstrate that known defenses are ineffective against universal perturbations. We propose an effective detection technique which can form the basis for robust defenses against attacks based on universal perturbations.

This mapping will be included in an AGV Picking Simulation Model that will be used for testing our routing strategies. Dijkstra's algorithm is an optimization algorithm that solves the single-source shortest path problem for a directed graph with weighted edges (non-negative weights). This length can be the absolute length of the path, it can also be computed considering other constraints situated on the edges or the nodes. These parameters will vary in time, therefore let's use a reinforcement learning approach to select the optimal route from these candidates in accordance with this state.

Inter-agent communication can significantly increase performance in multi-agent tasks that require co-ordination to achieve a shared goal. Prior work has shown that it is possible to learn inter-agent communication protocols using multi-agent reinforcement learning and message-passing network architectures. However, these models use an unconstrained broadcast communication model, in which an agent communicates with all other agents at every step, even when the task does not require it. In real-world applications, where communication may be limited by system constraints like bandwidth, power and network capacity, one might need to reduce the number of messages that are sent. In this work, we explore a simple method of minimizing communication while maximizing performance in multi-task learning: simultaneously optimizing a task-specific objective and a communication penalty. We show that the objectives can be optimized using Reinforce and the Gumbel-Softmax reparameterization. We introduce two techniques to stabilize training: 50% training and message forwarding. Training with the communication penalty on only 50% of the episodes prevents our models from turning off their outgoing messages. Second, repeating messages received previously helps models retain information, and further improves performance. With these techniques, we show that we can reduce communication by 75% with no loss of performance.

Reinforcement learning is a framework for interactive decision-making with incentives sequentially revealed across time without a system dynamics model. Due to its scaling to continuous spaces, we focus on policy search where one iteratively improves a parameterized policy with stochastic policy gradient (PG) updates. In tabular Markov Decision Problems (MDPs), under persistent exploration and suitable parameterization, global optimality may be obtained. By contrast, in continuous space, the non-convexity poses a pathological challenge as evidenced by existing convergence results being mostly limited to stationarity or arbitrary local extrema. To close this gap, we step towards persistent exploration in continuous space through policy parameterizations defined by distributions of heavier tails defined by tail-index parameter alpha, which increases the likelihood of jumping in state space. Doing so invalidates smoothness conditions of the score function common to PG. Thus, we establish how the convergence rate to stationarity depends on the policy's tail index alpha, a Holder continuity parameter, integrability conditions, and an exploration tolerance parameter introduced here for the first time. Further, we characterize the dependence of the set of local maxima on the tail index through an exit and transition time analysis of a suitably defined Markov chain, identifying that policies associated with Levy Processes of a heavier tail converge to wider peaks. This phenomenon yields improved stability to perturbations in supervised learning, which we corroborate also manifests in improved performance of policy search, especially when myopic and farsighted incentives are misaligned.

Green security domains feature defenders who plan patrols in the face of uncertainty about the adversarial behavior of poachers, illegal loggers, and illegal fishers. Importantly, the deterrence effect of patrols on adversaries' future behavior makes patrol planning a sequential decision-making problem. Therefore, we focus on robust sequential patrol planning for green security following the minimax regret criterion, which has not been considered in the literature. We formulate the problem as a game between the defender and nature who controls the parameter values of the adversarial behavior and design an algorithm MIRROR to find a robust policy. MIRROR uses two reinforcement learning-based oracles and solves a restricted game considering limited defender strategies and parameter values. We evaluate MIRROR on real-world poaching data.

While multitask representation learning has become a popular approach in reinforcement learning (RL), theoretical understanding of why and when it works remains limited. This paper presents analyses for the statistical benefit of multitask representation learning in linear Markov Decision Process (MDP) under a generative model. In this paper, we consider an agent to learn a representation function $\phi$ out of a function class $\Phi$ from $T$ source tasks with $N$ data per task, and then use the learned $\hat{\phi}$ to reduce the required number of sample for a new task. We first discover a \emph{Least-Activated-Feature-Abundance} (LAFA) criterion, denoted as $\kappa$, with which we prove that a straightforward least-square algorithm learns a policy which is $\tilde{O}(H^2\sqrt{\frac{\mathcal{C}(\Phi)^2 \kappa d}{NT}+\frac{\kappa d}{n}})$ sub-optimal. Here $H$ is the planning horizon, $\mathcal{C}(\Phi)$ is $\Phi$'s complexity measure, $d$ is the dimension of the representation (usually $d\ll \mathcal{C}(\Phi)$) and $n$ is the number of samples for the new task. Thus the required $n$ is $O(\kappa d H^4)$ for the sub-optimality to be close to zero, which is much smaller than $O(\mathcal{C}(\Phi)^2\kappa d H^4)$ in the setting without multitask representation learning, whose sub-optimality gap is $\tilde{O}(H^2\sqrt{\frac{\kappa \mathcal{C}(\Phi)^2d}{n}})$. This theoretically explains the power of multitask representation learning in reducing sample complexity. Further, we note that to ensure high sample efficiency, the LAFA criterion $\kappa$ should be small. In fact, $\kappa$ varies widely in magnitude depending on the different sampling distribution for new task. This indicates adaptive sampling technique is important to make $\kappa$ solely depend on $d$. Finally, we provide empirical results of a noisy grid-world environment to corroborate our theoretical findings.

Continuum robotic manipulators are increasingly adopted in minimal invasive surgery. However, their nonlinear behavior is challenging to model accurately, especially when subject to external interaction, potentially leading to poor control performance. In this letter, we investigate the feasibility of adopting a model-free multiagent reinforcement learning (RL), namely multiagent deep Q network (MADQN), to control a 2-degree of freedom (DoF) cable-driven continuum surgical manipulator. The control of the robot is formulated as a one-DoF, one agent problem in the MADQN framework to improve the learning efficiency. Combined with a shielding scheme that enables dynamic variation of the action set boundary, MADQN leads to efficient and importantly safer control of the robot. Shielded MADQN enabled the robot to perform point and trajectory tracking with submillimeter root mean square errors under external loads, soft obstacles, and rigid collision, which are common interaction scenarios encountered by surgical manipulators. The controller was further proven to be effective in a miniature continuum robot with high structural nonlinearitiy, achieving trajectory tracking with submillimeter accuracy under external payload.

Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process. DQN found this property might cause instability for training, so it proposed effective methods to handle the downside of the property. Instead of focusing on the unfavourable aspects, we find it critical for RL to ease the gap between the estimated data distribution and the ground truth data distribution while supervised learning (SL) fails to do so. From this new perspective, we extend the basic paradigm of RL called the Generalized Policy Iteration (GPI) into a more generalized version, which is called the Generalized Data Distribution Iteration (GDI). We see massive RL algorithms and techniques can be unified into the GDI paradigm, which can be considered as one of the special cases of GDI. We provide theoretical proof of why GDI is better than GPI and how it works. Several practical algorithms based on GDI have been proposed to verify the effectiveness and extensiveness of it. Empirical experiments prove our state-of-the-art (SOTA) performance on Arcade Learning Environment (ALE), wherein our algorithm has achieved 9620.98% mean human normalized score (HNS), 1146.39% median HNS and 22 human world record breakthroughs (HWRB) using only 200 training frames. Our work aims to lead the RL research to step into the journey of conquering the human world records and seek real superhuman agents on both performance and efficiency.

Online reinforcement learning (RL) has been widely applied in information processing scenarios, which usually exhibit much uncertainty due to the intrinsic randomness of channels and service demands. In this paper, we consider an un-discounted RL in general Markov decision processes (MDPs) with both endogeneous and exogeneous uncertainty, where both the rewards and state transition probability are unknown to the RL agent and evolve with the time as long as their respective variations do not exceed certain dynamic budget (i.e., upper bound). We first develop a variation-aware Bernstein-based upper confidence reinforcement learning (VB-UCRL), which we allow to restart according to a schedule dependent on the variations. We successfully overcome the challenges due to the exogeneous uncertainty and establish a regret bound of saving at most $\sqrt{S}$ or $S^{\frac{1}{6}}T^{\frac{1}{12}}$ compared with the latest results in the literature, where $S$ denotes the state size of the MDP and $T$ indicates the iteration index of learning steps.

So, say if we want to predict the future, rather than using the whole history, we can use the Markov State. The Markov State essentially contains no less information than the history. So, here the probability of getting to a future state St 1 given state St is the same as getting to St 1 given all the previous states. This is because the state St already contains the information about the previous states embedded in it. Say, we have a game in which there is a waiter at a restaurant.