Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where the trajectory distribution can be decomposed using the reparametrization trick. For this problem class, estimating the expected return is efficient and the trajectory can be computed deterministically given peripheral random variables, which enables us to study reparametrizable RL using supervised learning and transfer learning theory. Through these relationships, we derive guarantees on the gap between the expected and empirical return for both intrinsic and external errors, based on Rademacher complexity as well as the PAC-Bayes bound. Our bound suggests the generalization capability of reparameterizable RL is related to multiple factors including "smoothness" of the environment transition, reward and agent policy function class. We also empirically verify the relationship between the generalization gap and these factors through simulations.

Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general principle of advantage amplification that can overcome these hurdles through the use of temporal abstraction. We propose several aggregation methods and prove they induce amplification in certain settings. We also bound the loss in optimality incurred by our methods in environments where latent state evolves slowly and demonstrate their performance empirically in a stylized user-modeling task.

We study the sample complexity of approximate policy iteration (PI) for the Linear Quadratic Regulator (LQR), building on a recent line of work using LQR as a testbed to understand the limits of reinforcement learning (RL) algorithms on continuous control tasks. Our analysis quantifies the tension between policy improvement and policy evaluation, and suggests that policy evaluation is the dominant factor in terms of sample complexity. Specifically, we show that to obtain a controller that is within $\varepsilon$ of the optimal LQR controller, each step of policy evaluation requires at most $(n+d)^3/\varepsilon^2$ samples, where $n$ is the dimension of the state vector and $d$ is the dimension of the input vector. On the other hand, only $\log(1/\varepsilon)$ policy improvement steps suffice, resulting in an overall sample complexity of $(n+d)^3 \varepsilon^{-2} \log(1/\varepsilon)$. We furthermore build on our analysis and construct a simple adaptive procedure based on $\varepsilon$-greedy exploration which relies on approximate PI as a sub-routine and obtains $T^{2/3}$ regret, improving upon a recent result of Abbasi-Yadkori et al.

Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with a number of value-added services. Such a transformation---which will be fuelled by concomitant advances in technologies for machine learning (ML) and wireless communications---will enable a future vehicular ecosystem that is better featured and more efficient. However, there are lurking security problems related to the use of ML in such a critical setting where an incorrect ML decision may not only be a nuisance but can lead to loss of precious lives. In this paper, we present an in-depth overview of the various challenges associated with the application of ML in vehicular networks. In addition, we formulate the ML pipeline of CAVs and present various potential security issues associated with the adoption of ML methods. In particular, we focus on the perspective of adversarial ML attacks on CAVs and outline a solution to defend against adversarial attacks in multiple settings.

While previous approaches perform untargeted attacks on the state of the agent, we propose a method to perform targeted attacks to lure an agent into consistently following a desired policy. We place ourselves in a realistic setting, where attacks are performed on observations of the environment rather than the internal state of the agent and develop constant attacks instead of per-observation ones. We illustrate our method by attacking deep RL agents playing Atari games and show that universal additive masks can be applied not only to degrade performance but to take control of an agent.

We consider the Inverse Reinforcement Learning (IRL) problem in Contextual Markov Decision Processes (CMDPs). Here, the reward of the environment, which is not available to the agent, depends on a static parameter referred to as the context. Each context defines an MDP (with a different reward signal), and the agent is provided demonstrations by an expert, for different contexts. The goal is to learn a mapping from contexts to rewards, such that planning with respect to the induced reward will perform similarly to the expert, even for unseen contexts. We suggest two learning algorithms for this scenario. (1) For rewards that are a linear function of the context, we provide a method that is guaranteed to return an $\epsilon$-optimal solution after a polynomial number of demonstrations. (2) For general reward functions, we propose black-box descent methods based on evolutionary strategies capable of working with nonlinear estimators (e.g., neural networks). We evaluate our algorithms in autonomous driving and medical treatment simulations and demonstrate their ability to learn and generalize to unseen contexts.

Hierarchies are an effective way to boost sample efficiency in reinforcement learning, and computational efficiency in classical planning. However, acquiring hierarchies via hand-design (as in classical planning) is suboptimal, while acquiring them via end-to-end reward based training (as in reinforcement learning) is unstable and still prohibitively expensive. In this paper, we pursue an alternate paradigm for acquiring such hierarchical abstractions (or visuo-motor subroutines), via use of passive first person observation data. We use an inverse model trained on small amounts of interaction data to pseudo-label the passive first person videos with agent actions. Visuo-motor subroutines are acquired from these pseudo-labeled videos by learning a latent intent-conditioned policy that predicts the inferred pseudo-actions from the corresponding image observations. We demonstrate our proposed approach in context of navigation, and show that we can successfully learn consistent and diverse visuo-motor subroutines from passive first-person videos. We demonstrate the utility of our acquired visuo-motor subroutines by using them as is for exploration, and as sub-policies in a hierarchical RL framework for reaching point goals and semantic goals. We also demonstrate behavior of our subroutines in the real world, by deploying them on a real robotic platform. Project website with videos, code and data: https://ashishkumar1993.github.io/subroutines/.

We focus on the important problem of emergency evacuation, which clearly could benefit from reinforcement learning that has been largely unaddressed. Emergency evacuation is a complex task which is difficult to solve with reinforcement learning, since an emergency situation is highly dynamic, with a lot of changing variables and complex constraints that makes it difficult to train on. In this paper, we propose the first fire evacuation environment to train reinforcement learning agents for evacuation planning. The environment is modelled as a graph capturing the building structure. It consists of realistic features like fire spread, uncertainty and bottlenecks. We have implemented the environment in the OpenAI gym format, to facilitate future research. We also propose a new reinforcement learning approach that entails pretraining the network weights of a DQN based agents to incorporate information on the shortest path to the exit. We achieved this by using tabular Q-learning to learn the shortest path on the building model's graph. This information is transferred to the network by deliberately overfitting it on the Q-matrix. Then, the pretrained DQN model is trained on the fire evacuation environment to generate the optimal evacuation path under time varying conditions. We perform comparisons of the proposed approach with state-of-the-art reinforcement learning algorithms like PPO, VPG, SARSA, A2C and ACKTR. The results show that our method is able to outperform state-of-the-art models by a huge margin including the original DQN based models. Finally, we test our model on a large and complex real building consisting of 91 rooms, with the possibility to move to any other room, hence giving 8281 actions. We use an attention based mechanism to deal with large action spaces. Our model achieves near optimal performance on the real world emergency environment.

Once we start delving into the concepts behind Artificial Intelligence (AI) and Machine Learning (ML), we come across copious amounts of jargon related to this field of study. Understanding this jargon and how it can have an impact on the study related to ML goes a long way in comprehending the study that has been conducted by researchers and data scientists to get AI to the state it now is. In this article, I will be providing you with a comprehensive definition of supervised, unsupervised and reinforcement learning in the broader field of Machine Learning. You must have encountered these terms while hovering over articles pertaining to the progress made in AI and the role played by ML in propelling this success forward. Understanding these concepts is a given fact, and should not be compromised at any cost.

We consider a new form of model-based reinforcement learning methods that directly learns the optimal control parameters, instead of learning the underlying dynamical system. This includes a form of exploration and exploitation in learning and applying the optimal control parameters over time. This also includes a general framework that manages a collection of such control-model-based reinforcement learning methods running in parallel and that selects the best decision from among these parallel methods with the different methods interactively learning together. We derive theoretical results for the optimal control of linear and nonlinear instances of the new control-model-based reinforcement learning methods. Our empirical results demonstrate and quantify the significant benefits of our approach.