Intelligent Transportation Systems (ITS) have attracted the attention of researchers and the general public alike as a means to alleviate traffic congestion. Recently, the maturity of wireless technology has enabled a cost-efficient way to achieve ITS by detecting vehicles using Vehicle to Infrastructure (V2I) communications. Traditional ITS algorithms, in most cases, assume that every vehicle is observed, such as by a camera or a loop detector, but a V2I implementation would detect only those vehicles with wireless communications capability. We examine a family of transportation systems, which we will refer to as `Partially Detected Intelligent Transportation Systems'. An algorithm that can act well under a small detection rate is highly desirable due to gradual penetration rates of the underlying wireless technologies such as Dedicated Short Range Communications (DSRC) technology. Artificial Intelligence (AI) techniques for Reinforcement Learning (RL) are suitable tools for finding such an algorithm due to utilizing varied inputs and not requiring explicit analytic understanding or modeling of the underlying system dynamics. In this paper, we report a RL algorithm for partially observable ITS based on DSRC. The performance of this system is studied under different car flows, detection rates, and topologies of the road network. Our system is able to efficiently reduce the average waiting time of vehicles at an intersection, even with a low detection rate.

This work develops robust diffusion recursive least squares algorithms to mitigate the performance degradation often experienced in networks of agents in the presence of impulsive noise. The first algorithm minimizes an exponentially weighted least-squares cost function subject to a time-dependent constraint on the squared norm of the intermediate update at each node. A recursive strategy for computing the constraint is proposed using side information from the neighboring nodes to further improve the robustness. We also analyze the mean-square convergence behavior of the proposed algorithm. The second proposed algorithm is a modification of the first one based on the dichotomous coordinate descent iterations. It has a performance similar to that of the former, however its complexity is significantly lower especially when input regressors of agents have a shift structure and it is well suited to practical implementation. Simulations show the superiority of the proposed algorithms over previously reported techniques in various impulsive noise scenarios.

Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, reducing the number of samples needed, and that is easier to interpret. We evaluate several state representation learning methods on goal based robotics tasks and propose a new unsupervised model that stacks representations and combines strengths of several of these approaches. This method encodes all the relevant features, performs on par or better than end-to-end learning, and is robust to hyper-parameters change.

It seems like every day brings a new AI more capable than the last. This was recently apparent with AlphaGo--it was pretty great at beating Breakout, then Google got involved and soon it was capable of beating the world's leading Go champion. To do this, AlphaGo uses what is known as'deep reinforcement learning'. For example, in Breakout, it will take raw image frames of the game as it's being played. Whether or not the ball is hitting the bricks in those frames will decide whether or not positive reinforcement is registered.

In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime to improve its ability to solve new problems. We argue that previous experience with similar problems can provide an agent with information about how it should explore when facing a new but related problem. We show that the search for an optimal exploration strategy can be formulated as a reinforcement learning problem itself and demonstrate that such strategy can leverage patterns found in the structure of related problems. We conclude with experiments that show the benefits of optimizing an exploration strategy using our proposed approach.

This paper proposes the first model-free Reinforcement Learning (RL) framework to synthesise policies for an unknown, and possibly continuous-state, Markov Decision Process (MDP), such that a given linear temporal property is satisfied. We convert the given property into a Limit Deterministic Buchi Automaton (LDBA), namely a finite-state machine expressing the property. Exploiting the structure of the LDBA, we shape an adaptive reward function on-the-fly, so that an RL algorithm can synthesise a policy resulting in traces that probabilistically satisfy the linear temporal property. This probability (certificate) is also calculated in parallel with learning, i.e. the RL algorithm produces a policy that is certifiably safe with respect to the property. Under the assumption that the MDP has a finite number of states, theoretical guarantees are provided on the convergence of the RL algorithm. We also show that our method produces "best available" control policies when the logical property cannot be satisfied. Whenever the MDP has a continuous state space, we empirically show that our framework finds satisfying policies, if there exist such policies. Additionally, the proposed algorithm can handle time-varying periodic environments. The performance of the proposed architecture is evaluated via a set of numerical examples and benchmarks, where we observe an improvement of one order of magnitude in the number of iterations required for the policy synthesis, compared to existing approaches whenever available.

Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the machine to adapt to the users' intentions and preferences. Often, this takes the form of a human operator providing some type of feedback to the user, which can be explicit feedback, implicit feedback, or a combination of both. Explicit feedback, such as through a mouse click, carries a high cognitive load. The focus of this study is to extend the current state of the art in interactive machine learning by demonstrating that agents can learn a human user's behavior and adapt to preferences with a reduced amount of explicit human feedback in a mixed feedback setting. The learning agent perceives a value of its own behavior from hand gestures given via a spatial interface. This feedback mechanism is termed Spatial Interface Valuing. This method is evaluated experimentally in a simulated environment for a grasping task using a robotic arm with variable grip settings. Preliminary results indicate that learning agents using spatial interface valuing can learn a value function mapping spatial gestures to expected future rewards much more quickly as compared to those same agents just receiving explicit feedback, demonstrating that an agent perceiving feedback from a human user via a spatial interface can serve as an effective complement to existing approaches.

In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) and reinforcement learning (RL). More specifically, we first model the recommender-user interactive recommendation problem as an agent-environment RL task, which is mathematically described by a Markov decision process (MDP). Further, to achieve collaborative recommendations for the entire user community, we propose a novel CF-based MDP by encoding the states of all users into a shared latent vector space. Finally, we propose an effective Q-network learning method to learn the agent's optimal policy based on the CF-based MDP. The capability of CFRL is demonstrated by comparing its performance against a variety of existing methods on real-world datasets.

We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments. In our \textit{policy consolidation} model, the policy network interacts with a cascade of hidden networks that simultaneously remember the agent's policy at a range of timescales and regularise the current policy by its own history, thereby improving its ability to learn without forgetting. We find that the model improves continual learning relative to baselines on a number of continuous control tasks in single-task, alternating two-task, and multi-agent competitive self-play settings.

Stochastic approximation (SA) is a key method used in statistical learning. Recently, its non-asymptotic convergence analysis has been considered in many papers. However, most of the prior analyses are made under restrictive assumptions such as unbiased gradient estimates and convex objective function, which significantly limit their applications to sophisticated tasks such as online and reinforcement learning. These restrictions are all essentially relaxed in this work. In particular, we analyze a general SA scheme to minimize a non-convex, smooth objective function. We consider update procedure whose drift term depends on a state-dependent Markov chain and the mean field is not necessarily of gradient type, covering approximate second-order method and allowing asymptotic bias for the one-step updates. We illustrate these settings with the online EM algorithm and the policy-gradient method for average reward maximization in reinforcement learning.