We introduce a novel deep reinforcement learning (RL) approach called Movement Primitivebased Planning Policy (MP3). By integrating movement primitives (MPs) into the deep RL framework, MP3 enables the generation of smooth trajectories throughout the whole learning process while effectively learning from sparse and non-Markovian rewards. Additionally, MP3 maintains the capability to adapt to changes in the environment during execution. Although many early successes in robot RL have been achieved by combining RL with MPs, these approaches are often limited to learning single stroke-based motions, lacking the ability to adapt to task variations or adjust motions during execution. Building upon our previous work, which introduced an episode-based RL method for the non-linear adaptation of MP parameters to different task variations, this paper extends the approach to incorporating replanning strategies. This allows adaptation of the MP parameters throughout motion execution, addressing the lack of online motion adaptation in stochastic domains requiring feedback. We compared our approach against state-of-the-art deep RL and RL with MPs methods. The results demonstrated improved performance in sophisticated, sparse reward settings and in domains requiring replanning. The video demonstration can be accessed at https://intuitive-robots.github.io/mp3_website/.

In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is essentially different from supervised learning and in practice these learned optimizers do not work well even in simple RL tasks. We investigate this phenomenon and identity three issues. First, the gradients of an RL agent vary across a wide range in logarithms while their absolute values are in a small range, making neural networks hard to obtain accurate parameter updates. Second, the agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. Finally, due to highly stochastic agent-environment interactions, the agent-gradients have high bias and variance, which increase the difficulty of learning an optimizer for RL. We propose gradient processing, pipeline training, and a novel optimizer structure with good inductive bias to address these issues. By applying these techniques, for the first time, we show that learning an optimizer for RL from scratch is possible. Although only trained in toy tasks, our learned optimizer can generalize to unseen complex tasks in Brax.

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability that are assembled into multiscale systems, they hold great promise for realizing next-generation devices with exceptional, often exotic, functionalities. However, the vast design space and intricate structure-property relationships pose significant challenges in their design. A compelling paradigm that could bring the full potential of metamaterials to fruition is emerging: data-driven design. In this review, we provide a holistic overview of this rapidly evolving field, emphasizing the general methodology instead of specific domains and deployment contexts. We organize existing research into data-driven modules, encompassing data acquisition, machine learning-based unit cell design, and data-driven multiscale optimization. We further categorize the approaches within each module based on shared principles, analyze and compare strengths and applicability, explore connections between different modules, and identify open research questions and opportunities.

This paper addresses the problem of traversing through unknown, tilted, and narrow gaps for quadrotors using Deep Reinforcement Learning (DRL). Previous learning-based methods relied on accurate knowledge of the environment, including the gap's pose and size. In contrast, we integrate onboard sensing and detect the gap from a single onboard camera. The training problem is challenging for two reasons: a precise and robust whole-body planning and control policy is required for variable-tilted and narrow gaps, and an effective Sim2Real method is needed to successfully conduct real-world experiments. To this end, we propose a learning framework for agile gap traversal flight, which successfully trains the vehicle to traverse through the center of the gap at an approximate attitude to the gap with aggressive tilted angles. The policy trained only in a simulation environment can be transferred into different domains with fine-tuning while maintaining the success rate. Our proposed framework, which integrates onboard sensing and a neural network controller, achieves a success rate of 84.51% in real-world experiments, with gap orientations up to 60deg. To the best of our knowledge, this is the first paper that performs the learning-based variable-tilted narrow gap traversal flight in the real world, without prior knowledge of the environment.

Goal-conditioned hierarchical reinforcement learning (GCHRL) decomposes long-horizon tasks into sub-tasks through a hierarchical framework and it has demonstrated promising results across a variety of domains. However, the high-level policy's action space is often excessively large, presenting a significant challenge to effective exploration and resulting in potentially inefficient training. Moreover, the dynamic variability of the low-level policy introduces non-stationarity to the high-level state transition function, significantly impeding the learning of the high-level policy. In this paper, we design a measure of prospect for subgoals by planning in the goal space based on the goal-conditioned value function. Building upon the measure of prospect, we propose a landmark-guided exploration strategy by integrating the measures of prospect and novelty which aims to guide the agent to explore efficiently and improve sample efficiency. To address the non-stationarity arising from the dynamic changes of the low-level policy, we apply a state-specific regularization to the learning of low-level policy, which facilitates stable learning of the hierarchical policy. The experimental results demonstrate that our proposed exploration strategy significantly outperforms the baseline methods across multiple tasks.

Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy. Unlike other algorithms for hierarchical sampling that optimize a variational bound, GFlowNet algorithms can stably run off-policy, which can be advantageous for discovering modes of the target distribution. Despite this flexibility in the choice of behaviour policy, the optimal way of efficiently selecting trajectories for training has not yet been systematically explored. In this paper, we view the choice of trajectories for training as an active learning problem and approach it using Bayesian techniques inspired by methods for multi-armed bandits. The proposed algorithm, Thompson sampling GFlowNets (TS-GFN), maintains an approximate posterior distribution over policies and samples trajectories from this posterior for training. We show in two domains that TS-GFN yields improved exploration and thus faster convergence to the target distribution than the off-policy exploration strategies used in past work.

This paper addresses the efficient management of Mobile Access Points (MAPs), which are Unmanned Aerial Vehicles (UAV), in 5G networks. We propose a two-level hierarchical architecture, which dynamically reconfigures the network while considering Integrated Access-Backhaul (IAB) constraints. The high-layer decision process determines the number of MAPs through consensus, and we develop a joint optimization process to account for co-dependence in network self-management. In the low-layer, MAPs manage their placement using a double-attention based Deep Reinforcement Learning (DRL) model that encourages cooperation without retraining. To improve generalization and reduce complexity, we propose a federated mechanism for training and sharing one placement model for every MAP in the low-layer. Additionally, we jointly optimize the placement and backhaul connectivity of MAPs using a multi-objective reward function, considering the impact of varying MAP placement on wireless backhaul connectivity.

Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-free policy that optimizes a risk-sensitive criterion based on the conditional value at risk. The risk-sensitive objective function is modeled using an input-convex neural network ensuring convexity with respect to the actions and enabling the identification of globally optimal actions through simple gradient-following methods. Experimental results demonstrate the efficacy of our approach in maintaining effective risk control.

Reliable real-world deployment of reinforcement learning (RL) methods requires a nuanced understanding of their strengths and weaknesses and how they compare to those of humans. Human-machine systems are becoming more prevalent and the design of these systems relies on a task-oriented understanding of both human learning (HL) and RL. Thus, an important line of research is characterizing how the structure of a learning task affects learning performance. While increasingly complex benchmark environments have led to improved RL capabilities, such environments are difficult to use for the dedicated study of task structure. To address this challenge we present a learning environment built to support rigorous study of the impact of task structure on HL and RL. We demonstrate the environment's utility for such study through example experiments in task structure that show performance differences between humans and RL algorithms.

The design of induction machine is a challenging task due to different electromagnetic and thermal constraints. Quick estimation of machine's dimensions is important in the sales tool to provide quick quotations to customers based on specific requirements. The key part of this process is to select different design parameters like length, diameter, tooth tip height and winding turns to achieve certain torque, current and temperature of the machine. Electrical machine designers, with their experience know how to alter different machine design parameters to achieve a customer specific operation requirements. We propose a reinforcement learning algorithm to design a customised induction motor. The neural network model is trained off-line by simulating different instances of of electrical machine design game with a reward or penalty function when a good or bad design choice is made. The results demonstrate that the suggested method automates electrical machine design without applying any human engineering knowledge.