While the real world application of reinforcement learning (RL) is becoming popular, the safety concern and the robustness of an RL system require more attention. A recent work reveals that, in a multi-agent RL environment, backdoor trigger actions can be injected into a victim agent (a.k.a. trojan agent), which can result in a catastrophic failure as soon as it sees the backdoor trigger action. We propose the problem of RL Backdoor Detection, aiming to address this safety vulnerability. An interesting observation we drew from extensive empirical studies is a trigger smoothness property where normal actions similar to the backdoor trigger actions can also trigger low performance of the trojan agent. Inspired by this observation, we propose a reinforcement learning solution TrojanSeeker to find approximate trigger actions for the trojan agents, and further propose an efficient approach to mitigate the trojan agents based on machine unlearning. Experiments show that our approach can correctly distinguish and mitigate all the trojan agents across various types of agents and environments.

In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose to evaluate the robustness of c-MARL agents via a model-based approach. Our proposed formulation can craft stronger adversarial state perturbations of c-MARL agents(s) to lower total team rewards more than existing model-free approaches. In addition, we propose the first victim-agent selection strategy which allows us to develop even stronger adversarial attack. Numerical experiments on multi-agent MuJoCo benchmarks illustrate the advantage of our approach over other baselines. The proposed model-based attack consistently outperforms other baselines in all tested environments.

We propose a new framework for imitation learning - treating imitation as a two-player ranking-based Stackelberg game between a $\textit{policy}$ and a $\textit{reward}$ function. In this game, the reward agent learns to satisfy pairwise performance rankings within a set of policies, while the policy agent learns to maximize this reward. This game encompasses a large subset of both inverse reinforcement learning (IRL) methods and methods which learn from offline preferences. The Stackelberg game formulation allows us to use optimization methods that take the game structure into account, leading to more sample efficient and stable learning dynamics compared to existing IRL methods. We theoretically analyze the requirements of the loss function used for ranking policy performances to facilitate near-optimal imitation learning at equilibrium. We use insights from this analysis to further increase sample efficiency of the ranking game by using automatically generated rankings or with offline annotated rankings. Our experiments show that the proposed method achieves state-of-the-art sample efficiency and is able to solve previously unsolvable tasks in the Learning from Observation (LfO) setting.

Reusing previously trained models is critical in deep reinforcement learning to speed up training of new agents. However, it is unclear how to acquire new skills when objectives and constraints are in conflict with previously learned skills. Moreover, when retraining, there is an intrinsic conflict between exploiting what has already been learned and exploring new skills. In soft actor-critic (SAC) methods, a temperature parameter can be dynamically adjusted to weight the action entropy and balance the explore $\times$ exploit trade-off. However, controlling a single coefficient can be challenging within the context of retraining, even more so when goals are contradictory. In this work, inspired by neuroscience research, we propose a novel approach using inhibitory networks to allow separate and adaptive state value evaluations, as well as distinct automatic entropy tuning. Ultimately, our approach allows for controlling inhibition to handle conflict between exploiting less risky, acquired behaviors and exploring novel ones to overcome more challenging tasks. We validate our method through experiments in OpenAI Gym environments.

Fast and reliable wireless communication has become a critical demand in human life. When natural disasters strike, providing ubiquitous connectivity becomes challenging by using traditional wireless networks. In this context, unmanned aerial vehicle (UAV) based aerial networks offer a promising alternative for fast, flexible, and reliable wireless communications in mission-critical (MC) scenarios. Due to the unique characteristics such as mobility, flexible deployment, and rapid reconfiguration, drones can readily change location dynamically to provide on-demand communications to users on the ground in emergency scenarios. As a result, the usage of UAV base stations (UAV-BSs) has been considered as an appropriate approach for providing rapid connection in MC scenarios. In this paper, we study how to control a UAV-BS in both static and dynamic environments. We investigate a situation in which a macro BS is destroyed as a result of a natural disaster and a UAV-BS is deployed using integrated access and backhaul (IAB) technology to provide coverage for users in the disaster area. We present a data collection system, signaling procedures and machine learning applications for this use case. A deep reinforcement learning algorithm is developed to jointly optimize the tilt of the access and backhaul antennas of the UAV-BS as well as its three-dimensional placement. Evaluation results show that the proposed algorithm can autonomously navigate and configure the UAV-BS to satisfactorily serve the MC users on the ground.

RL algorithms can be broadly categorized as model-free and model-based. Model-free algorithms do not build an explicit model of the environment, or more rigorously, the MDP. They are closer to trial-and-error algorithms that run experiments with the environment using actions and derive the optimal policy from it directly. Model-free algorithms are either value-based or policy-based. Value-based algorithms consider optimal policy to be a direct result of estimating the value function of every state accurately.

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for developing scalable approaches for solving long-horizon problems. While previous works have looked at the possibility of using symbolic models along with RL approaches, they tend to assume that the high-level action models are executable at low level and the fluents can exclusively characterize all desirable MDP states. This need not be true and this assumption overlooks one of the central technical challenges of incorporating symbolic task knowledge, namely, that these symbolic models are going to be an incomplete representation of the underlying task. To this end, we introduce Symbolic-Model Guided Reinforcement Learning, wherein we will formalize the relationship between the symbolic model and the underlying MDP that will allow us to capture the incompleteness of the symbolic model. We will use these models to extract high-level landmarks that will be used to decompose the task, and at the low level, we learn a set of diverse policies for each possible task sub-goal identified by the landmark. We evaluate our system by testing on three different benchmark domains and we show how even with incomplete symbolic model information, our approach is able to discover the task structure and efficiently guide the RL agent towards the goal.

We introduce Synthetic Environments (SEs) and Reward Networks (RNs), represented by neural networks, as proxy environment models for training Reinforcement Learning (RL) agents. We show that an agent, after being trained exclusively on the SE, is able to solve the corresponding real environment. While an SE acts as a full proxy to a real environment by learning about its state dynamics and rewards, an RN is a partial proxy that learns to augment or replace rewards. We use bi-level optimization to evolve SEs and RNs: the inner loop trains the RL agent, and the outer loop trains the parameters of the SE / RN via an evolution strategy. We evaluate our proposed new concept on a broad range of RL algorithms and classic control environments. In a one-to-one comparison, learning an SE proxy requires more interactions with the real environment than training agents only on the real environment. However, once such an SE has been learned, we do not need any interactions with the real environment to train new agents. Moreover, the learned SE proxies allow us to train agents with fewer interactions while maintaining the original task performance. Our empirical results suggest that SEs achieve this result by learning informed representations that bias the agents towards relevant states. Moreover, we find that these proxies are robust against hyperparameter variation and can also transfer to unseen agents.

Federated Learning (FL) over wireless network enables data-conscious services by leveraging the ubiquitous intelligence at network edge for privacy-preserving model training. As the proliferation of context-aware services, the diversified personal preferences causes disagreeing conditional distributions among user data, which leads to poor inference performance. In this sense, clustered federated learning is proposed to group user devices with similar preference and provide each cluster with a personalized model. This calls for innovative design in edge association that involves user clustering and also resource management optimization. We formulate an accuracy-cost trade-off optimization problem by jointly considering model accuracy, communication resource allocation and energy consumption. To comply with parameter encryption techniques in FL, we propose an iterative solution procedure which employs deep reinforcement learning based approach at cloud server for edge association. The reward function consists of minimized energy consumption at each base station and the averaged model accuracy of all users. Under our proposed solution, multiple edge base station are fully exploited to realize cost efficient personalized federated learning without any prior knowledge on model parameters. Simulation results show that our proposed strategy outperforms existing strategies in achieving accurate learning at low energy cost.

Nowadays, fast delivery services have created the need for high-density warehouses. The puzzle-based storage system is a practical way to enhance the storage density, however, facing difficulties in the retrieval process. In this work, a deep reinforcement learning algorithm, specifically the Double&Dueling Deep Q Network, is developed to solve the multi-item retrieval problem in the system with general settings, where multiple desired items, escorts, and I/O points are placed randomly. Additionally, we propose a general compact integer programming model to evaluate the solution quality. Extensive numerical experiments demonstrate that the reinforcement learning approach can yield high-quality solutions and outperforms three related state-of-the-art heuristic algorithms. Furthermore, a conversion algorithm and a decomposition framework are proposed to handle simultaneous movement and large-scale instances respectively, thus improving the applicability of the PBS system.