The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather data via vehicle-to-vehicle (V2V) communication, such as processed LIDAR and camera data from other vehicles. In this work, we design an integrated information sharing and safe multi-agent reinforcement learning (MARL) framework for CAVs, to take advantage of the extra information when making decisions to improve traffic efficiency and safety. We first use weight pruned convolutional neural networks (CNN) to process the raw image and point cloud LIDAR data locally at each autonomous vehicle, and share CNN-output data with neighboring CAVs. We then design a safe actor-critic algorithm that utilizes both a vehicle's local observation and the information received via V2V communication to explore an efficient behavior planning policy with safety guarantees. Using the CARLA simulator for experiments, we show that our approach improves the CAV system's efficiency in terms of average velocity and comfort under different CAV ratios and different traffic densities. We also show that our approach avoids the execution of unsafe actions and always maintains a safe distance from other vehicles. We construct an obstacle-at-corner scenario to show that the shared vision can help CAVs to observe obstacles earlier and take action to avoid traffic jams.

This paper explores the potential of event cameras to enable continuous time reinforcement learning. We formalise this problem where a continuous stream of unsynchronised observations is used to produce a corresponding stream of output actions for the environment. This lack of synchronisation enables greatly enhanced reactivity. We present a method to train on event streams derived from standard RL environments, thereby solving the proposed continuous time RL problem. The CERiL algorithm uses specialised network layers which operate directly on an event stream, rather than aggregating events into quantised image frames. We show the advantages of event streams over less-frequent RGB images. The proposed system outperforms networks typically used in RL, even succeeding at tasks which cannot be solved traditionally. We also demonstrate the value of our CERiL approach over a standard SNN baseline using event streams.

In this paper, we study both multi-armed and contextual bandit problems in censored environments. Our goal is to estimate the performance loss due to censorship in the context of classical algorithms designed for uncensored environments. Our main contributions include the introduction of a broad class of censorship models and their analysis in terms of the effective dimension of the problem -- a natural measure of its underlying statistical complexity and main driver of the regret bound. In particular, the effective dimension allows us to maintain the structure of the original problem at first order, while embedding it in a bigger space, and thus naturally leads to results analogous to uncensored settings. Our analysis involves a continuous generalization of the Elliptical Potential Inequality, which we believe is of independent interest. We also discover an interesting property of decision-making under censorship: a transient phase during which initial misspecification of censorship is self-corrected at an extra cost, followed by a stationary phase that reflects the inherent slowdown of learning governed by the effective dimension. Our results are useful for applications of sequential decision-making models where the feedback received depends on strategic uncertainty (e.g., agents' willingness to follow a recommendation) and/or random uncertainty (e.g., loss or delay in arrival of information).

Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods are among those cutting-edge solutions. However, traditional methods that learn the value function as a monotonic mixing of per-agent utilities cannot solve the tasks with non-monotonic returns. This hinders their application in generic scenarios. Recent methods tackle this problem from the perspective of implicit credit assignment by learning value functions with complete expressiveness or using additional structures to improve cooperation. However, they are either difficult to learn due to large joint action spaces or insufficient to capture the complicated interactions among agents which are essential to solving tasks with non-monotonic returns. To address these problems, we propose a novel explicit credit assignment method to address the non-monotonic problem. Our method, Adaptive Value decomposition with Greedy Marginal contribution (AVGM), is based on an adaptive value decomposition that learns the cooperative value of a group of dynamically changing agents. We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios. Then, our method uses a greedy marginal contribution computed from the value decomposition as an individual credit to incentivize agents to learn the optimal cooperative policy. We further extend the module with an action encoder to guarantee the linear time complexity for computing the greedy marginal contribution. Experimental results demonstrate that our method achieves significant performance improvements in several non-monotonic domains.

Reinforcement learning (RL) describes the interaction between a learning agent and an unknown environment, where the agent aims to maximize the cumulative reward through trial and error Sutton and Barto [2018]. It has achieved great success in many real applications, such as games [Mnih et al., 2013; Silver et al., 2016], robotics [Kober et al., 2013; Lillicrap et al., 2015], autonomous driving [Kiran et al., 2021] and recommendation systems [Afsar et al., 2022; Lin et al., 2021]. The interaction in RL is commonly portrayed by Markov decision processes (MDP). Most of the works study the stochastic setting, where the reward is sampled from a fixed distribution [Azar et al., 2017; Jin et al., 2018; Simchowitz and Jamieson, 2019; Yang et al., 2021]. RL in real applications is in general more challenging than the stochastic setting, as the environment could be nonstationary and the reward function could be adaptive towards the agent's policy. For example, a scheduling algorithm will be deployed to self-interested parties, and recommendation algorithms will face strategic users. To design robust algorithms that work under non-stationary environments, a line of works focuses on the adversarial setting, where the reward function could be arbitrarily chosen by an adversary [Yu et al., 2009; Rosenberg and Mansour, 2019; Jin et al., 2020a; Chen et al., 2021; Luo et al., 2021a].

Semiconductor manufacturing is a notoriously complex and costly multi-step process involving a long sequence of operations on expensive and quantity-limited equipment. Recent chip shortages and their impacts have highlighted the importance of semiconductors in the global supply chains and how reliant on those our daily lives are. Due to the investment cost, environmental impact, and time scale needed to build new factories, it is difficult to ramp up production when demand spikes. This work introduces a method to successfully learn to schedule a semiconductor manufacturing facility more efficiently using deep reinforcement and self-supervised learning. We propose the first adaptive scheduling approach to handle complex, continuous, stochastic, dynamic, modern semiconductor manufacturing models. Our method outperforms the traditional hierarchical dispatching strategies typically used in semiconductor manufacturing plants, substantially reducing each order's tardiness and time until completion. As a result, our method yields a better allocation of resources in the semiconductor manufacturing process.

MuZero Unplugged presents a promising approach for offline policy learning from logged data. It conducts Monte-Carlo Tree Search (MCTS) with a learned model and leverages Reanalyze algorithm to learn purely from offline data. For good performance, MCTS requires accurate learned models and a large number of simulations, thus costing huge computing time. This paper investigates a few hypotheses where MuZero Unplugged may not work well under the offline RL settings, including 1) learning with limited data coverage; 2) learning from offline data of stochastic environments; 3) improperly parameterized models given the offline data; 4) with a low compute budget. We propose to use a regularized one-step look-ahead approach to tackle the above issues. Instead of planning with the expensive MCTS, we use the learned model to construct an advantage estimation based on a one-step rollout. Policy improvements are towards the direction that maximizes the estimated advantage with regularization of the dataset. We conduct extensive empirical studies with BSuite environments to verify the hypotheses and then run our algorithm on the RL Unplugged Atari benchmark. Experimental results show that our proposed approach achieves stable performance even with an inaccurate learned model. On the large-scale Atari benchmark, the proposed method outperforms MuZero Unplugged by 43%. Most significantly, it uses only 5.6% wall-clock time (i.e., 1 hour) compared to MuZero Unplugged (i.e., 17.8 hours) to achieve a 150% IQM normalized score with the same hardware and software stacks. Our implementation is open-sourced at https://github.com/sail-sg/rosmo.

The Bitcoin cryptocurrency has received much attention recently. In the network of Bitcoin, transactions are recorded in a ledger. In this network, the process of recording transactions depends on some nodes called miners that execute a protocol known as mining protocol. One of the significant aspects of mining protocol is incentive compatibility. However, literature has shown that Bitcoin mining's protocol is not incentive-compatible. Some nodes with high computational power can obtain more revenue than their fair share by adopting a type of attack called the selfish mining attack. In this paper, we propose an artificial intelligence-based defense against selfish mining attacks by applying the theory of learning automata. The proposed defense mechanism ignores private blocks by assigning weight based on block discovery time and changes current Bitcoin's fork resolving policy by evaluating branches' height difference in a self-adaptive manner utilizing learning automata. To the best of our knowledge, the proposed protocol is the literature's first learning-based defense mechanism. Simulation results have shown the superiority of the proposed mechanism against tie-breaking mechanism, which is a well-known defense. The simulation results have shown that the suggested defense mechanism increases the profit threshold up to 40\% and decreases the revenue of selfish attackers.

A deep reinforcement learning technique is presented for task offloading decision-making algorithms for a multi-access edge computing (MEC) assisted unmanned aerial vehicle (UAV) network in a smart farm Internet of Things (IoT) environment. The task offloading technique uses financial concepts such as cost functions and conditional variable at risk (CVaR) in order to quantify the damage that may be caused by each risky action. The approach was able to quantify potential risks to train the reinforcement learning agent to avoid risky behaviors that will lead to irreversible consequences for the farm. Such consequences include an undetected fire, pest infestation, or a UAV being unusable. The proposed CVaR-based technique was compared to other deep reinforcement learning techniques and two fixed rule-based techniques. The simulation results show that the CVaR-based risk quantifying method eliminated the most dangerous risk, which was exceeding the deadline for a fire detection task. As a result, it reduced the total number of deadline violations with a negligible increase in energy consumption.

This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives, such as Double DQN, even though the former uses significantly more memory and computation. The fundamental problem is that learned models can be inaccurate and often generate invalid states, especially when iterated many steps. In this paper, we avoid this limitation by constraining background planning to a set of (abstract) subgoals and learning only local, subgoal-conditioned models. This goal-space planning (GSP) approach is more computationally efficient, naturally incorporates temporal abstraction for faster long-horizon planning and avoids learning the transition dynamics entirely. We show that our GSP algorithm can learn significantly faster than a Double DQN baseline in a variety of situations.