This paper addresses the problem of optimizing charging/discharging schedules of electric vehicles (EVs) when participate in demand response (DR). As there exist uncertainties in EVs' remaining energy, arrival and departure time, and future electricity prices, it is quite difficult to make charging decisions to minimize charging cost while guarantee that the EV's battery state-of-the-charge (SOC) is within certain range. To handle with this dilemma, this paper formulates the EV charging scheduling problem as a constrained Markov decision process (CMDP). By synergistically combining the augmented Lagrangian method and soft actor critic algorithm, a novel safe off-policy reinforcement learning (RL) approach is proposed in this paper to solve the CMDP. The actor network is updated in a policy gradient manner with the Lagrangian value function. A double-critics network is adopted to synchronously estimate the action-value function to avoid overestimation bias. The proposed algorithm does not require strong convexity guarantee of examined problems and is sample efficient. Comprehensive numerical experiments with real-world electricity price demonstrate that our proposed algorithm can achieve high solution optimality and constraints compliance.

The Euclidean Steiner tree problem seeks the min-cost network to connect a collection of target locations, and it underlies many applications of wireless networks. In this paper, we present a study on solving the Euclidean Steiner tree problem using reinforcement learning enhanced by graph representation learning. Different from the commonly studied connectivity problems like travelling salesman problem or vehicle routing problem where the search space is finite, the Euclidean Steiner tree problem requires to search over the entire Euclidean space, thereby making the existing methods not applicable. In this paper, we design discretization methods by leveraging the unique characteristics of the Steiner tree, and propose new training schemes for handling the dynamic Steiner points emerging during the incremental construction. Our design is examined through a sanity check using experiments on a collection of datasets, with encouraging results demonstrating the utility of our method as an alternative to classic combinatorial methods.

Despite the emerging progress of integrating evolutionary computation into reinforcement learning, the absence of a high-performance platform endowing composability and massive parallelism causes non-trivial difficulties for research and applications related to asynchronous commercial games. Here we introduce Lamarckian - an open-source platform featuring support for evolutionary reinforcement learning scalable to distributed computing resources. To improve the training speed and data efficiency, Lamarckian adopts optimized communication methods and an asynchronous evolutionary reinforcement learning workflow. To meet the demand for an asynchronous interface by commercial games and various methods, Lamarckian tailors an asynchronous Markov Decision Process interface and designs an object-oriented software architecture with decoupled modules. In comparison with the state-of-the-art RLlib, we empirically demonstrate the unique advantages of Lamarckian on benchmark tests with up to 6000 CPU cores: i) both the sampling efficiency and training speed are doubled when running PPO on Google football game; ii) the training speed is 13 times faster when running PBT+PPO on Pong game. Moreover, we also present two use cases: i) how Lamarckian is applied to generating behavior-diverse game AI; ii) how Lamarckian is applied to game balancing tests for an asynchronous commercial game.

Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents. However, many transfer techniques in reinforcement learning make the limiting assumption that the teacher is an expert. In this paper, we use the action prior from the Reinforcement Learning as Inference framework - that is, a distribution over actions at each state which resembles a teacher policy, rather than a Bayesian prior - to recover state-of-the-art policy distillation techniques. Then, we propose a class of adaptive methods that can robustly exploit action priors by combining reward shaping and auxiliary regularization losses. In contrast to prior work, we develop algorithms for leveraging suboptimal action priors that may nevertheless impart valuable knowledge - which we call soft action priors. The proposed algorithms adapt by adjusting the strength of teacher feedback according to an estimate of the teacher's usefulness in each state. We perform tabular experiments, which show that the proposed methods achieve state-of-the-art performance, surpassing it when learning from suboptimal priors. Finally, we demonstrate the robustness of the adaptive algorithms in continuous action deep RL problems, in which adaptive algorithms considerably improved stability when compared to existing policy distillation methods.

In cooperative multi-agent reinforcement learning, centralized training and decentralized execution (CTDE) has achieved remarkable success. Individual Global Max (IGM) decomposition, which is an important element of CTDE, measures the consistency between local and joint policies. The majority of IGM-based research focuses on how to establish this consistent relationship, but little attention has been paid to examining IGM's potential flaws. In this work, we reveal that the IGM condition is a lossy decomposition, and the error of lossy decomposition will accumulated in hypernetwork-based methods. To address the above issue, we propose to adopt an imitation learning strategy to separate the lossy decomposition from Bellman iterations, thereby avoiding error accumulation. The proposed strategy is theoretically proved and empirically verified on the StarCraft Multi-Agent Challenge benchmark problem with zero sight view. The results also confirm that the proposed method outperforms state-of-the-art IGM-based approaches.

Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance. However, the gradient conflict problem is still poorly understood in Meta-RL, which may lead to performance degradation when encountering distinct tasks. To tackle this challenge, this paper proposes a novel personalized Meta-RL (pMeta-RL) algorithm, which aggregates task-specific personalized policies to update a meta-policy used for all tasks, while maintaining personalized policies to maximize the average return of each task under the constraint of the meta-policy. We also provide the theoretical analysis under the tabular setting, which demonstrates the convergence of our pMeta-RL algorithm. Moreover, we extend the proposed pMeta-RL algorithm to a deep network version based on soft actor-critic, making it suitable for continuous control tasks. Experiment results show that the proposed algorithms outperform other previous Meta-RL algorithms on Gym and MuJoCo suites.

Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which suggests it is feasible to create a generalizable controller through meta-learning. In this work, we formulate a meta reinforcement learning (meta-RL) control strategy that can be used to tune proportional--integral controllers. Our meta-RL agent has a recurrent structure that accumulates "context" to learn a system's dynamics through a hidden state variable in closed-loop. This architecture enables the agent to automatically adapt to changes in the process dynamics. In tests reported here, the meta-RL agent was trained entirely offline on first order plus time delay systems, and produced excellent results on novel systems drawn from the same distribution of process dynamics used for training. A key design element is the ability to leverage model-based information offline during training in simulated environments while maintaining a model-free policy structure for interacting with novel processes where there is uncertainty regarding the true process dynamics. Meta-learning is a promising approach for constructing sample-efficient intelligent controllers.

Traditionally, an agent maximizes a reward defined according to the task to perform: it may be a score when the agent learns to solve a game or a distance function when the agent learns to reach a goal. The reward is then considered as extrinsic (or as a feedback) because the reward function is provided expertly and specifically for the task. With an extrinsic reward, many spectacular results have been obtained on Atari game [Bellemare et al. 2015] with the Deep Q-network (DQN) [Mnih et al. 2015] through the integration of deep learning to RL, leading to deep reinforcement learning (DRL). However, despite the recent improvements of DRL approaches, they turn out to be most of the time unsuccessful when the rewards are scattered in the environment, as the agent is then unable to learn the desired behavior for the targeted task [Francois-Lavet et al. 2018]. Moreover, the behaviors learned by the agent are hardly reusable, both within the same task and across many different tasks [Francois-Lavet et al. 2018]. It is difficult for an agent to generalize the learnt skills to make high-level decisions in the environment. For example, such skill could be go to the door using primitive actions consisting in moving in the four cardinal directions; or even to move forward controlling different joints of a humanoid robot like in the robotic simulator MuJoCo [Todorov et al. 2012]. On another side, unlike RL, developmental learning [Cangelosi and Schlesinger 2018; Oudeyer and Smith 2016; Piaget and Cook 1952] is based on the trend that babies, or more broadly organisms, acquire new skill while spontaneously exploring their environment [Barto 2013; Gopnik et al. 1999].

Meta-learning is a branch of machine learning which aims to synthesize data from a distribution of related tasks to efficiently solve new ones. In process control, many systems have similar and well-understood dynamics, which suggests it is feasible to create a generalizable controller through meta-learning. In this work, we formulate a meta reinforcement learning (meta-RL) control strategy that takes advantage of known, offline information for training, such as a model structure. The meta-RL agent is trained over a distribution of model parameters, rather than a single model, enabling the agent to automatically adapt to changes in the process dynamics while maintaining performance. A key design element is the ability to leverage model-based information offline during training, while maintaining a model-free policy structure for interacting with new environments. Our previous work has demonstrated how this approach can be applied to the industrially-relevant problem of tuning proportional-integral controllers to control first order processes. In this work, we briefly reintroduce our methodology and demonstrate how it can be extended to proportional-integral-derivative controllers and second order systems.

This paper develops a model-based reinforcement learning (MBRL) framework for learning online the value function of an infinite-horizon optimal control problem while obeying safety constraints expressed as control barrier functions (CBFs). Our approach is facilitated by the development of a novel class of CBFs, termed Lyapunov-like CBFs (LCBFs), that retain the beneficial properties of CBFs for developing minimally-invasive safe control policies while also possessing desirable Lyapunov-like qualities such as positive semi-definiteness. We show how these LCBFs can be used to augment a learning-based control policy to guarantee safety and then leverage this approach to develop a safe exploration framework in a MBRL setting. We demonstrate that our approach can handle more general safety constraints than comparative methods via numerical examples.