The flavor is the focal point in the flavor industry, which follows social tendencies and behaviors. The research and development of new flavoring agents and molecules are essential in this field. On the other hand, the development of natural flavors plays a critical role in modern society. In light of this, the present work proposes a novel framework based on Scientific Machine Learning to undertake an emerging problem in flavor engineering and industry. Therefore, this work brings an innovative methodology to design new natural flavor molecules. The molecules are evaluated regarding the synthetic accessibility, the number of atoms, and the likeness to a natural or pseudo-natural product.

Previous works showed that Deep-RL can be applied to perform mapless navigation, including the medium transition of Hybrid Unmanned Aerial Underwater Vehicles (HUAUVs). This paper presents new approaches based on the state-of-the-art actor-critic algorithms to address the navigation and medium transition problems for a HUAUV. We show that a double critic Deep-RL with Recurrent Neural Networks improves the navigation performance of HUAUVs using solely range data and relative localization. Our Deep-RL approaches achieved better navigation and transitioning capabilities with a solid generalization of learning through distinct simulated scenarios, outperforming previous approaches.

Existing data-driven and feedback traffic control strategies do not consider the heterogeneity of real-time data measurements. Besides, traditional reinforcement learning (RL) methods for traffic control usually converge slowly for lacking data efficiency. Moreover, conventional optimal perimeter control schemes require exact knowledge of the system dynamics and thus would be fragile to endogenous uncertainties. To handle these challenges, this work proposes an integral reinforcement learning (IRL) based approach to learning the macroscopic traffic dynamics for adaptive optimal perimeter control. This work makes the following primary contributions to the transportation literature: (a) A continuous-time control is developed with discrete gain updates to adapt to the discrete-time sensor data. (b) To reduce the sampling complexity and use the available data more efficiently, the experience replay (ER) technique is introduced to the IRL algorithm. (c) The proposed method relaxes the requirement on model calibration in a "model-free" manner that enables robustness against modeling uncertainty and enhances the real-time performance via a data-driven RL algorithm. (d) The convergence of the IRL-based algorithms and the stability of the controlled traffic dynamics are proven via the Lyapunov theory. The optimal control law is parameterized and then approximated by neural networks (NN), which moderates the computational complexity. Both state and input constraints are considered while no model linearization is required. Numerical examples and simulation experiments are presented to verify the effectiveness and efficiency of the proposed method.

We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections. Particularly, in the proposed framework, a manager agent learns to divide mTSPTWR into sub-routing tasks by assigning customers to each vehicle via a Graph Isomorphism Network (GIN) based policy network. A worker agent learns to solve sub-routing tasks by minimizing the cost in terms of both tour length and rejection rate for each vehicle, the maximum of which is then fed back to the manager agent to learn better assignments. Experimental results demonstrate that the proposed framework outperforms strong baselines in terms of higher solution quality and shorter computation time. More importantly, the trained agents also achieve competitive performance for solving unseen larger instances.

Deterministic and Stochastic techniques in Deep Reinforcement Learning (Deep-RL) have become a promising solution to improve motion control and the decision-making tasks for a wide variety of robots. Previous works showed that these Deep-RL algorithms can be applied to perform mapless navigation of mobile robots in general. However, they tend to use simple sensing strategies since it has been shown that they perform poorly with a high dimensional state spaces, such as the ones yielded from image-based sensing. This paper presents a comparative analysis of two Deep-RL techniques - Deep Deterministic Policy Gradients (DDPG) and Soft Actor-Critic (SAC) - when performing tasks of mapless navigation for mobile robots. We aim to contribute by showing how the neural network architecture influences the learning itself, presenting quantitative results based on the time and distance of navigation of aerial mobile robots for each approach. Overall, our analysis of six distinct architectures highlights that the stochastic approach (SAC) better suits with deeper architectures, while the opposite happens with the deterministic approach (DDPG).

The ability to accelerate the design of biological sequences can have a substantial impact on the progress of the medical field. The problem can be framed as a global optimization problem where the objective is an expensive black-box function such that we can query large batches restricted with a limitation of a low number of rounds. Bayesian Optimization is a principled method for tackling this problem. However, the astronomically large state space of biological sequences renders brute-force iterating over all possible sequences infeasible. In this paper, we propose MetaRLBO where we train an autoregressive generative model via Meta-Reinforcement Learning to propose promising sequences for selection via Bayesian Optimization. We pose this problem as that of finding an optimal policy over a distribution of MDPs induced by sampling subsets of the data acquired in the previous rounds. Our in-silico experiments show that meta-learning over such ensembles provides robustness against reward misspecification and achieves competitive results compared to existing strong baselines.

Flocking is a very challenging problem in a multi-agent system; traditional flocking methods also require complete knowledge of the environment and a precise model for control. In this paper, we propose Evolutionary Multi-Agent Reinforcement Learning (EMARL) in flocking tasks, a hybrid algorithm that combines cooperation and competition with little prior knowledge. As for cooperation, we design the agents' reward for flocking tasks according to the boids model. While for competition, agents with high fitness are designed as senior agents, and those with low fitness are designed as junior, letting junior agents inherit the parameters of senior agents stochastically. To intensify competition, we also design an evolutionary selection mechanism that shows effectiveness on credit assignment in flocking tasks. Experimental results in a range of challenging and self-contrast benchmarks demonstrate that EMARL significantly outperforms the full competition or cooperation methods.

Solving temporally-extended tasks is a challenge for most reinforcement learning (RL) algorithms [arXiv:1906.07343]. We investigate the ability of an RL agent to learn to ask natural language questions as a tool to understand its environment and achieve greater generalisation performance in novel, temporally-extended environments. We do this by endowing this agent with the ability of asking "yes-no" questions to an all-knowing Oracle. This allows the agent to obtain guidance regarding the task at hand, while limiting the access to new information. To study the emergence of such natural language questions in the context of temporally-extended tasks we first train our agent in a Mini-Grid environment. We then transfer the trained agent to a different, harder environment. We observe a significant increase in generalisation performance compared to a baseline agent unable to ask questions. Through grounding its understanding of natural language in its environment, the agent can reason about the dynamics of its environment to the point that it can ask new, relevant questions when deployed in a novel environment.

Generalizable object manipulation skills are critical for intelligent and multi-functional robots to work in real-world complex scenes. Despite the recent progress in reinforcement learning, it is still very challenging to learn a generalizable manipulation policy that can handle a category of geometrically diverse articulated objects. In this work, we tackle this category-level object manipulation policy learning problem via imitation learning in a task-agnostic manner, where we assume no handcrafted dense rewards but only a terminal reward. Given this novel and challenging generalizable policy learning problem, we identify several key issues that can fail the previous imitation learning algorithms and hinder the generalization to unseen instances. We then propose several general but critical techniques, including generative adversarial self-imitation learning from demonstrations, progressive growing of discriminator, and instance-balancing for expert buffer, that accurately pinpoints and tackles these issues and can benefit category-level manipulation policy learning regardless of the tasks. Our experiments on ManiSkill benchmarks demonstrate a remarkable improvement on all tasks and our ablation studies further validate the contribution of each proposed technique.

A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to save real-world samples. However, when the learned model has a non-negligible model error, sequential steps in the model are hard to be accurately evaluated, limiting the model's utilization. This paper proposes to alleviate this issue by introducing multi-step plans to replace multi-step actions for model-based RL. We employ the multi-step plan value estimation, which evaluates the expected discounted return after executing a sequence of action plans at a given state, and updates the policy by directly computing the multi-step policy gradient via plan value estimation. The new model-based reinforcement learning algorithm MPPVE (Model-based Planning Policy Learning with Multi-step Plan Value Estimation) shows a better utilization of the learned model and achieves a better sample efficiency than state-of-the-art model-based RL approaches.