Reinforcement learning (RL) is a promising method to solve control problems. However, model-free RL algorithms are sample inefficient and require thousands if not millions of samples to learn optimal control policies. A major source of computational cost in RL corresponds to the transition function, which is dictated by the model dynamics. This is especially problematic when model dynamics is represented with coupled PDEs. In such cases, the transition function often involves solving a large-scale discretization of the said PDEs. We propose a multilevel RL framework in order to ease this cost by exploiting sublevel models that correspond to coarser scale discretization (i.e. multilevel models). This is done by formulating an approximate multilevel Monte Carlo estimate of the objective function of the policy and / or value network instead of Monte Carlo estimates, as done in the classical framework. As a demonstration of this framework, we present a multilevel version of the proximal policy optimization (PPO) algorithm. Here, the level refers to the grid fidelity of the chosen simulation-based environment. We provide two examples of simulation-based environments that employ stochastic PDEs that are solved using finite-volume discretization. For the case studies presented, we observed substantial computational savings using multilevel PPO compared to its classical counterpart.

Additive Manufacturing (AM) is a powerful technology that produces complex 3D geometries using various materials in a layer-by-layer fashion. However, quality assurance is the main challenge in AM industry due to the possible time-varying processing conditions during AM process. Notably, new defects may occur during printing, which cannot be mitigated by offline analysis tools that focus on existing defects. This challenge motivates this work to develop online learning-based methods to deal with the new defects during printing. Since AM typically fabricates a small number of customized products, this paper aims to create an online learning-based strategy to mitigate the new defects in AM process while minimizing the number of samples needed. The proposed method is based on model-free Reinforcement Learning (RL). It is called Continual G-learning since it transfers several sources of prior knowledge to reduce the needed training samples in the AM process. Offline knowledge is obtained from literature, while online knowledge is learned during printing. The proposed method develops a new algorithm for learning the optimal defect mitigation strategies proven the best performance when utilizing both knowledge sources. Numerical and real-world case studies in a fused filament fabrication (FFF) platform are performed and demonstrate the effectiveness of the proposed method.

A significant challenge in reinforcement learning is quantifying the complex relationship between actions and long-term rewards. The effects may manifest themselves over a long sequence of state-action pairs, making them hard to pinpoint. In this paper, we propose a method to link transitions with significant deviations in state with unusually large variations in subsequent rewards. Such transitions are marked as possible causal effects, and the corresponding state-action pairs are added to a separate replay buffer. In addition, we include \textit{contrastive} samples corresponding to transitions from a similar state but with differing actions. Including this Contrastive Experience Replay (CER) during training is shown to outperform standard value-based methods on 2D navigation tasks. We believe that CER can be useful for a broad class of learning tasks, including for any off-policy reinforcement learning algorithm.

Compared to standard retrieval tasks, passage retrieval for conversational question answering (CQA) poses new challenges in understanding the current user question, as each question needs to be interpreted within the dialogue context. Moreover, it can be expensive to re-train well-established retrievers such as search engines that are originally developed for non-conversational queries. To facilitate their use, we develop a query rewriting model CONQRR that rewrites a conversational question in the context into a standalone question. It is trained with a novel reward function to directly optimize towards retrieval using reinforcement learning and can be adapted to any off-the-shelf retriever. CONQRR achieves state-of-the-art results on a recent open-domain CQA dataset containing conversations from three different sources, and is effective for two different off-the-shelf retrievers. Our extensive analysis also shows the robustness of CONQRR to out-of-domain dialogues as well as to zero query rewriting supervision.

We consider the task of estimating a structural model of dynamic decisions by a human agent based upon the observable history of implemented actions and visited states. This problem has an inherent nested structure: in the inner problem, an optimal policy for a given reward function is identified while in the outer problem, a measure of fit is maximized. Several approaches have been proposed to alleviate the computational burden of this nested-loop structure, but these methods still suffer from high complexity when the state space is either discrete with large cardinality or continuous in high dimensions. Other approaches in the inverse reinforcement learning (IRL) literature emphasize policy estimation at the expense of reduced reward estimation accuracy. In this paper we propose a single-loop estimation algorithm with finite time guarantees that is equipped to deal with high-dimensional state spaces without compromising reward estimation accuracy. In the proposed algorithm, each policy improvement step is followed by a stochastic gradient step for likelihood maximization. We show that the proposed algorithm converges to a stationary solution with a finite-time guarantee. Further, if the reward is parameterized linearly, we show that the algorithm approximates the maximum likelihood estimator sublinearly. Finally, by using robotics control problems in MuJoCo and their transfer settings, we show that the proposed algorithm achieves superior performance compared with other IRL and imitation learning benchmarks.

As shown by recent studies, machine intelligence-enabled systems are vulnerable to test cases resulting from either adversarial manipulation or natural distribution shifts. This has raised great concerns about deploying machine learning algorithms for real-world applications, especially in safety-critical domains such as autonomous driving (AD). On the other hand, traditional AD testing on naturalistic scenarios requires hundreds of millions of driving miles due to the high dimensionality and rareness of the safety-critical scenarios in the real world. As a result, several approaches for autonomous driving evaluation have been explored, which are usually, however, based on different simulation platforms, types of safety-critical scenarios, scenario generation algorithms, and driving route variations. Thus, despite a large amount of effort in autonomous driving testing, it is still challenging to compare and understand the effectiveness and efficiency of different testing scenario generation algorithms and testing mechanisms under similar conditions. In this paper, we aim to provide the first unified platform SafeBench to integrate different types of safety-critical testing scenarios, scenario generation algorithms, and other variations such as driving routes and environments. Meanwhile, we implement 4 deep reinforcement learning-based AD algorithms with 4 types of input (e.g., bird's-eye view, camera) to perform fair comparisons on SafeBench. We find our generated testing scenarios are indeed more challenging and observe the trade-off between the performance of AD agents under benign and safety-critical testing scenarios. We believe our unified platform SafeBench for large-scale and effective autonomous driving testing will motivate the development of new testing scenario generation and safe AD algorithms. SafeBench is available at https://safebench.github.io.

Reinforcement learning (RL) trains many agents, which is resource-intensive and must scale to large GPU clusters. Different RL training algorithms offer different opportunities for distributing and parallelising the computation. Yet, current distributed RL systems tie the definition of RL algorithms to their distributed execution: they hard-code particular distribution strategies and only accelerate specific parts of the computation (e.g. policy network updates) on GPU workers. Fundamentally, current systems lack abstractions that decouple RL algorithms from their execution. We describe MindSpore Reinforcement Learning (MSRL), a distributed RL training system that supports distribution policies that govern how RL training computation is parallelised and distributed on cluster resources, without requiring changes to the algorithm implementation. MSRL introduces the new abstraction of a fragmented dataflow graph, which maps Python functions from an RL algorithm's training loop to parallel computational fragments. Fragments are executed on different devices by translating them to low-level dataflow representations, e.g. computational graphs as supported by deep learning engines, CUDA implementations or multi-threaded CPU processes. We show that MSRL subsumes the distribution strategies of existing systems, while scaling RL training to 64 GPUs.

Model-based offline reinforcement learning (RL) aims to find highly rewarding policy, by leveraging a previously collected static dataset and a dynamics model. While the dynamics model learned through reuse of the static dataset, its generalization ability hopefully promotes policy learning if properly utilized. To that end, several works propose to quantify the uncertainty of predicted dynamics, and explicitly apply it to penalize reward. However, as the dynamics and the reward are intrinsically different factors in context of MDP, characterizing the impact of dynamics uncertainty through reward penalty may incur unexpected tradeoff between model utilization and risk avoidance. In this work, we instead maintain a belief distribution over dynamics, and evaluate/optimize policy through biased sampling from the belief. The sampling procedure, biased towards pessimism, is derived based on an alternating Markov game formulation of offline RL. We formally show that the biased sampling naturally induces an updated dynamics belief with policy-dependent reweighting factor, termed Pessimism-Modulated Dynamics Belief. To improve policy, we devise an iterative regularized policy optimization algorithm for the game, with guarantee of monotonous improvement under certain condition. To make practical, we further devise an offline RL algorithm to approximately find the solution. Empirical results show that the proposed approach achieves state-of-the-art performance on a wide range of benchmark tasks.

Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract multi-agent decision making into an SM problem and benefit from the prosperous development of SMs. In this paper, we introduce a novel architecture named Multi-Agent Transformer (MAT) that effectively casts cooperative multi-agent reinforcement learning (MARL) into SM problems wherein the task is to map agents' observation sequence to agents' optimal action sequence. Our goal is to build the bridge between MARL and SMs so that the modeling power of modern sequence models can be unleashed for MARL. Central to our MAT is an encoder-decoder architecture which leverages the multi-agent advantage decomposition theorem to transform the joint policy search problem into a sequential decision making process; this renders only linear time complexity for multi-agent problems and, most importantly, endows MAT with monotonic performance improvement guarantee. Unlike prior arts such as Decision Transformer fit only pre-collected offline data, MAT is trained by online trials and errors from the environment in an on-policy fashion. To validate MAT, we conduct extensive experiments on StarCraftII, Multi-Agent MuJoCo, Dexterous Hands Manipulation, and Google Research Football benchmarks. Results demonstrate that MAT achieves superior performance and data efficiency compared to strong baselines including MAPPO and HAPPO. Furthermore, we demonstrate that MAT is an excellent few-short learner on unseen tasks regardless of changes in the number of agents. See our project page at https://sites.google.com/view/multi-agent-transformer.

Deploying ultra-dense networks that operate on millimeter wave (mmWave) band is a promising way to address the tremendous growth on mobile data traffic. However, one key challenge of ultra-dense mmWave network (UDmmN) is beam management due to the high propagation delay, limited beam coverage as well as numerous beams and users. In this paper, a novel systematic beam control scheme is presented to tackle the beam management problem which is difficult due to the nonconvex objective function. We employ double deep Q-network (DDQN) under a federated learning (FL) framework to address the above optimization problem, and thereby fulfilling adaptive and intelligent beam management in UDmmN. In the proposed beam management scheme based on FL (BMFL), the non-rawdata aggregation can theoretically protect user privacy while reducing handoff cost. Moreover, we propose to adopt a data cleaning technique in the local model training for BMFL, with the aim to further strengthen the privacy protection of users while improving the learning convergence speed. Simulation results demonstrate the performance gain of our proposed scheme.