Reinforcement learning techniques achieved human-level performance in several tasks in the last decade. However, in recent years, the need for interpretability emerged: we want to be able to understand how a system works and the reasons behind its decisions. Not only we need interpretability to assess the safety of the produced systems, we also need it to extract knowledge about unknown problems. While some techniques that optimize decision trees for reinforcement learning do exist, they usually employ greedy algorithms or they do not exploit the rewards given by the environment. This means that these techniques may easily get stuck in local optima. In this work, we propose a novel approach to interpretable reinforcement learning that uses decision trees. We present a two-level optimization scheme that combines the advantages of evolutionary algorithms with the advantages of Q-learning. This way we decompose the problem into two sub-problems: the problem of finding a meaningful and useful decomposition of the state space, and the problem of associating an action to each state. We test the proposed method on three well-known reinforcement learning benchmarks, on which it results competitive with respect to the state-of-the-art in both performance and interpretability. Finally, we perform an ablation study that confirms that using the two-level optimization scheme gives a boost in performance in non-trivial environments with respect to a one-layer optimization technique.

The Indian Institute of Technology Madras has developed a fellowship program to encourage early-career AI researchers. The Narayanan Family Foundation and the Institute's Robert Bosch Centre for Data Science and AI have teamed up to build a fellowship in Artificial Intelligence for Social Good. The application is available to artificial intelligence researchers who want to use their skills for the betterment. The Indian Institute of Technology Madras hopes to attract recent PhD graduates or newly qualified researchers in computer science, computational and data sciences, biomedical sciences, management, finance, and other engineering departments with outstanding educational achievements to RBCDSAI through this program, which is funded by the Narayanan Family Foundation. With India's largest network analytics and deep reinforcement learning study groups, RBCDSAI is a world's most prominent interdisciplinary research academic centre for Data Science and AI.

Model-predictive-control (MPC) offers an optimal control technique to establish and ensure that the total operation cost of multi-energy systems remains at a minimum while fulfilling all system constraints. However, this method presumes an adequate model of the underlying system dynamics, which is prone to modelling errors and is not necessarily adaptive. This has an associated initial and ongoing project-specific engineering cost. In this paper, we present an on- and off-policy multi-objective reinforcement learning (RL) approach, that does not assume a model a priori, benchmarking this against a linear MPC (LMPC - to reflect current practice, though non-linear MPC performs better) - both derived from the general optimal control problem, highlighting their differences and similarities. In a simple multi-energy system (MES) configuration case study, we show that a twin delayed deep deterministic policy gradient (TD3) RL agent offers potential to match and outperform the perfect foresight LMPC benchmark (101.5%). This while the realistic LMPC, i.e. imperfect predictions, only achieves 98%. While in a more complex MES system configuration, the RL agent's performance is generally lower (94.6%), yet still better than the realistic LMPC (88.9%). In both case studies, the RL agents outperformed the realistic LMPC after a training period of 2 years using quarterly interactions with the environment. We conclude that reinforcement learning is a viable optimal control technique for multi-energy systems given adequate constraint handling and pre-training, to avoid unsafe interactions and long training periods, as is proposed in fundamental future work.

Combination of machine learning (for generating machine intelligence), computer vision (for better environment perception), and robotic systems (for controlled environment interaction) motivates this work toward proposing a vision-based learning framework for intelligent robot control as the ultimate goal (vision-based learning robot). This work specifically introduces deep reinforcement learning as the the learning framework, a General-purpose framework for AI (AGI) meaning application-independent and platform-independent. In terms of robot control, this framework is proposing specifically a high-level control architecture independent of the low-level control, meaning these two required level of control can be developed separately from each other. In this aspect, the high-level control creates the required intelligence for the control of the platform using the recorded low-level controlling data from that same platform generated by a trainer. The recorded low-level controlling data is simply indicating the successful and failed experiences or sequences of experiments conducted by a trainer using the same robotic platform. The sequences of the recorded data are composed of observation data (input sensor), generated reward (feedback value) and action data (output controller). For experimental platform and experiments, vision sensors are used for perception of the environment, different kinematic controllers create the required motion commands based on the platform application, deep learning approaches generate the required intelligence, and finally reinforcement learning techniques incrementally improve the generated intelligence until the mission is accomplished by the robot.

This paper develops a reinforcement learning (RL) scheme for adaptive traffic signal control (ATSC), called "CVLight", that leverages data collected only from connected vehicles (CV). Seven types of RL models are proposed within this scheme that contain various state and reward representations, including incorporation of CV delay and green light duration into state and the usage of CV delay as reward. To further incorporate information of both CV and non-CV into CVLight, an algorithm based on actor-critic, A2C-Full, is proposed where both CV and non-CV information is used to train the critic network, while only CV information is used to update the policy network and execute optimal signal timing. These models are compared at an isolated intersection under various CV market penetration rates. A full model with the best performance (i.e., minimum average travel delay per vehicle) is then selected and applied to compare with state-of-the-art benchmarks under different levels of traffic demands, turning proportions, and dynamic traffic demands, respectively. Two case studies are performed on an isolated intersection and a corridor with three consecutive intersections located in Manhattan, New York, to further demonstrate the effectiveness of the proposed algorithm under real-world scenarios. Compared to other baseline models that use all vehicle information, the trained CVLight agent can efficiently control multiple intersections solely based on CV data and can achieve a similar or even greater performance when the CV penetration rate is no less than 20%.

Research seeks to apply Artificial Intelligence (AI) to scale and extend the capabilities of human operators to defend networks. A fundamental problem that hinders the generalization of successful AI approaches -- i.e., beating humans at playing games -- is that network defense cannot be defined as a single game with a fixed set of rules. Our position is that network defense is better characterized as a collection of games with uncertain and possibly drifting rules. Hence, we propose to define network defense tasks as distributions of network environments, to: (i) enable research to apply modern AI techniques, such as unsupervised curriculum learning and reinforcement learning for network defense; and, (ii) facilitate the design of well-defined challenges that can be used to compare approaches for autonomous cyberdefense. To demonstrate that an approach for autonomous network defense is practical it is important to be able to reason about the boundaries of its applicability. Hence, we need to be able to define network defense tasks that capture sets of adversarial tactics, techniques, and procedures (TTPs); quality of service (QoS) requirements; and TTPs available to defenders. Furthermore, the abstractions to define these tasks must be extensible; must be backed by well-defined semantics that allow us to reason about distributions of environments; and should enable the generation of data and experiences from which an agent can learn. Our approach named Network Environment Design for Autonomous Cyberdefense inspired the architecture of FARLAND, a Framework for Advanced Reinforcement Learning for Autonomous Network Defense, which we use at MITRE to develop RL network defenders that perform blue actions from the MITRE Shield matrix against attackers with TTPs that drift from MITRE ATT&CK TTPs.

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the task, but also provide sufficient shaping to accomplish it. In this paper, we discuss a new perspective on reinforcement learning, recasting it as the problem of inferring actions that achieve desired outcomes, rather than a problem of maximizing rewards. To solve the resulting outcome-directed inference problem, we establish a novel variational inference formulation that allows us to derive a well-shaped reward function which can be learned directly from environment interactions. From the corresponding variational objective, we also derive a new probabilistic Bellman backup operator reminiscent of the standard Bellman backup operator and use it to develop an off-policy algorithm to solve goal-directed tasks. We empirically demonstrate that this method eliminates the need to design reward functions and leads to effective goal-directed behaviors.

Model-based reinforcement learning is a compelling framework for data-efficient learning of agents that interact with the world. This family of algorithms has many subcomponents that need to be carefully selected and tuned. As a result the entry-bar for researchers to approach the field and to deploy it in real-world tasks can be daunting. In this paper, we present MBRL-Lib -- a machine learning library for model-based reinforcement learning in continuous state-action spaces based on PyTorch. MBRL-Lib is designed as a platform for both researchers, to easily develop, debug and compare new algorithms, and non-expert user, to lower the entry-bar of deploying state-of-the-art algorithms. MBRL-Lib is open-source at https://github.com/facebookresearch/mbrl-lib.

Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste. This paper proposes a novel multi-agent reinforcement learning method, named KS-DDPG (Knowledge Sharing Deep Deterministic Policy Gradient) to achieve optimal control by enhancing the cooperation between traffic signals. By introducing the knowledge-sharing enabled communication protocol, each agent can access to the collective representation of the traffic environment collected by all agents. The proposed method is evaluated through two experiments respectively using synthetic and real-world datasets. The comparison with state-of-the-art reinforcement learning-based and conventional transportation methods demonstrate the proposed KS-DDPG has significant efficiency in controlling large-scale transportation networks and coping with fluctuations in traffic flow. In addition, the introduced communication mechanism has also been proven to speed up the convergence of the model without significantly increasing the computational burden.

There is a growing interest in the area of machine learning and creativity. This survey presents an overview of the history and the state of the art of computational creativity theories, machine learning techniques, including generative deep learning, and corresponding automatic evaluation methods. After presenting a critical discussion of the key contributions in this area, we outline the current research challenges and emerging opportunities in this field.