Getting robots to navigate to multiple objects autonomously is essential yet difficult in robot applications. One of the key challenges is how to explore environments efficiently with camera sensors only. Existing navigation methods mainly focus on fixed cameras and few attempts have been made to navigate with active cameras. As a result, the agent may take a very long time to perceive the environment due to limited camera scope. In contrast, humans typically gain a larger field of view by looking around for a better perception of the environment. How to make robots perceive the environment as efficiently as humans is a fundamental problem in robotics. In this paper, we consider navigating to multiple objects more efficiently with active cameras. Specifically, we cast moving camera to a Markov Decision Process and reformulate the active camera problem as a reinforcement learning problem. However, we have to address two new challenges: 1) how to learn a good camera policy in complex environments and 2) how to coordinate it with the navigation policy. To address these, we carefully design a reward function to encourage the agent to explore more areas by moving camera actively. Moreover, we exploit human experience to infer a rule-based camera action to guide the learning process. Last, to better coordinate two kinds of policies, the camera policy takes navigation actions into account when making camera moving decisions. Experimental results show our camera policy consistently improves the performance of multi-object navigation over four baselines on two datasets.

Accurate localization is a critical requirement for most robotic tasks. The main body of existing work is focused on passive localization in which the motions of the robot are assumed given, abstracting from their influence on sampling informative observations. While recent work has shown the benefits of learning motions to disambiguate the robot's poses, these methods are restricted to granular discrete actions and directly depend on the size of the global map. We propose Active Particle Filter Networks (APFN), an approach that only relies on local information for both the likelihood evaluation as well as the decision making. To do so, we couple differentiable particle filters with a reinforcement learning agent that attends to the most relevant parts of the map. The resulting approach inherits the computational benefits of particle filters and can directly act in continuous action spaces while remaining fully differentiable and thereby end-to-end optimizable as well as agnostic to the input modality. We demonstrate the benefits of our approach with extensive experiments in photorealistic indoor environments built from real-world 3D scanned apartments. Videos and code are available at http://apfn.cs.uni-freiburg.de.

Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure. This paper explores algorithm design in the continuous time domain, with finite-horizon optimal control objective. The main contributions are (i) Algorithm design is based on a new Q-ODE, which defines the model-free characterization of the Hamilton-Jacobi-Bellman equation. (ii) The Q-ODE motivates a new formulation of Convex Q-learning that avoids the approximations appearing in prior work. The Bellman error used in the algorithm is defined by filtered measurements, which is beneficial in the presence of measurement noise. (iii) A characterization of boundedness of the constraint region is obtained through a non-trivial extension of recent results from the discrete time setting. (iv) The theory is illustrated in application to resource allocation for distributed energy resources, for which the theory is ideally suited.

This paper investigates the network load balancing problem in data centers (DCs) where multiple load balancers (LBs) are deployed, using the multi-agent reinforcement learning (MARL) framework. The challenges of this problem consist of the heterogeneous processing architecture and dynamic environments, as well as limited and partial observability of each LB agent in distributed networking systems, which can largely degrade the performance of in-production load balancing algorithms in real-world setups. Centralised-training-decentralised-execution (CTDE) RL scheme has been proposed to improve MARL performance, yet it incurs -- especially in distributed networking systems, which prefer distributed and plug-and-play design scheme -- additional communication and management overhead among agents. We formulate the multi-agent load balancing problem as a Markov potential game, with a carefully and properly designed workload distribution fairness as the potential function. A fully distributed MARL algorithm is proposed to approximate the Nash equilibrium of the game. Experimental evaluations involve both an event-driven simulator and real-world system, where the proposed MARL load balancing algorithm shows close-to-optimal performance in simulations, and superior results over in-production LBs in the real-world system.

The uses of robots are changing from static environments in factories to encompass novel concepts such as Human-Robot Collaboration in unstructured settings. Pre-programming all the functionalities for robots becomes impractical, and hence, robots need to learn how to react to new events autonomously, just like humans. However, humans, unlike machines, are naturally skilled in responding to unexpected circumstances based on either experiences or observations. Hence, embedding such anthropoid behaviours into robots entails the development of neuro-cognitive models that emulate motor skills under a robot learning paradigm. Effective encoding of these skills is bound to the proper choice of tools and techniques. This paper studies different motion and behaviour learning methods ranging from Movement Primitives (MP) to Experience Abstraction (EA), applied to different robotic tasks. These methods are scrutinized and then experimentally benchmarked by reconstructing a standard pick-n-place task. Apart from providing a standard guideline for the selection of strategies and algorithms, this paper aims to draw a perspectives on their possible extensions and improvements

The ability to reuse previous policies is an important aspect of human intelligence. To achieve efficient policy reuse, a Deep Reinforcement Learning (DRL) agent needs to decide when to reuse and which source policies to reuse. Previous methods solve this problem by introducing extra components to the underlying algorithm, such as hierarchical high-level policies over source policies, or estimations of source policies' value functions on the target task. However, training these components induces either optimization non-stationarity or heavy sampling cost, significantly impairing the effectiveness of transfer. To tackle this problem, we propose a novel policy reuse algorithm called Critic-gUided Policy reuse (CUP), which avoids training any extra components and efficiently reuses source policies. CUP utilizes the critic, a common component in actor-critic methods, to evaluate and choose source policies. At each state, CUP chooses the source policy that has the largest one-step improvement over the current target policy, and forms a guidance policy. The guidance policy is theoretically guaranteed to be a monotonic improvement over the current target policy. Then the target policy is regularized to imitate the guidance policy to perform efficient policy search. Empirical results demonstrate that CUP achieves efficient transfer and significantly outperforms baseline algorithms.

Deep Reinforcement Learning is an advanced type of machine learning in which an AI application solves very complex problems, usually to achieve a goal. On our blog, we recently discussed how deep reinforcement learning takes machine learning to another level of performance. With Deep reinforcement learning, a machine can become more predictive. A machine learns from its mistakes, corrects them, and achieves complex goals such as winning a game or figuring out the fastest route for a self-driving car to travel amid constantly changing variables such as traffic patterns and weather conditions. Recently, DeepMind made a major breakthrough with deep reinforcement learning that has captured the attention of the business and technology world.

Have you ever thought about what would happen if you combined the power of machine learning and artificial intelligence with financial engineering? Today, you can stop imagining, and start doing. This course will teach you the core fundamentals of financial engineering, with a machine learning twist. We will cover must-know topics in financial engineering, such as: Exploratory data analysis, significance testing, correlations, alpha and beta Time series analysis, simple moving average, exponentially-weighted moving average Holt-Winters exponential smoothing model Efficient Market Hypothesis Random Walk Hypothesis Time series forecasting ("stock price prediction") Modern portfolio theory Efficient frontier / Markowitz bullet Mean-variance optimization Maximizing the Sharpe ratio Convex optimization with Linear Programming and Quadratic Programming Capital Asset Pricing Model (CAPM) Algorithmic trading (VIP only) Statistical Factor Models (VIP only) Regime Detection with Hidden Markov Models (VIP only) In addition, we will look at various non-traditional techniques which stem purely from the field of machine learning and artificial intelligence, such as: Classification models Unsupervised learning Reinforcement learning and Q-learning We will learn about the greatest flub made in the past decade by marketers posing as "machine learning experts" who promise to teach unsuspecting students how to "predict stock prices with LSTMs". You will learn exactly why their methodology is fundamentally flawed and why their results are complete nonsense.

This course will introduce you to the state of the art in Reinforcement Learning techniques. It will also prepare you for the next courses in this series, where we will explore other advanced methods that excel in other types of task. The course is focused on developing practical skills. Therefore, after learning the most important concepts of each family of methods, we will implement one or more of their algorithms in jupyter notebooks, from scratch.

In this work, we point out the problem of observed adversaries for deep policies. Specifically, recent work has shown that deep reinforcement learning is susceptible to adversarial attacks where an observed adversary acts under environmental constraints to invoke natural but adversarial observations. This setting is particularly relevant for HRI since HRI-related robots are expected to perform their tasks around and with other agents. In this work, we demonstrate that this effect persists even with low-dimensional observations. We further show that these adversarial attacks transfer across victims, which potentially allows malicious attackers to train an adversary without access to the target victim.