Micro robotics is quickly emerging to be a promising technological solution to many medical treatments with focus on targeted drug delivery. They are effective when working in swarms whose individual control is mostly infeasible owing to their minute size. Controlling a number of robots with a single controller is thus important and artificial intelligence can help us perform this task successfully. In this work, we use the Reinforcement Learning (RL) algorithms Proximal Policy Optimization (PPO) and Robust Policy Optimization (RPO) to navigate a swarm of 4, 9 and 16 microswimmers under hydrodynamic effects, controlled by their orientation, towards a circular absorbing target. We look at both PPO and RPO performances with limited state information scenarios and also test their robustness for random target location and size. We use curriculum learning to improve upon the performance and demonstrate the same in learning to navigate a swarm of 25 swimmers and steering the swarm to exemplify the manoeuvring capabilities of the RL model.

With the commercial application of automated vehicles (AVs), the sharing of roads between AVs and human-driven vehicles (HVs) becomes a common occurrence in the future. While research has focused on improving the safety and reliability of autonomous driving, it's also crucial to consider collaboration between AVs and HVs. Human-like interaction is a required capability for AVs, especially at common unsignalized intersections, as human drivers of HVs expect to maintain their driving habits for inter-vehicle interactions. This paper uses the social value orientation (SVO) in the decision-making of vehicles to describe the social interaction among multiple vehicles. Specifically, we define the quantitative calculation of the conflict-involved SVO at unsignalized intersections to enhance decision-making based on the reinforcement learning method. We use naturalistic driving scenarios with highly interactive motions for performance evaluation of the proposed method. Experimental results show that SVO is more effective in characterizing inter-vehicle interactions than conventional motion state parameters like velocity, and the proposed method can accurately reproduce naturalistic driving trajectories compared to behavior cloning.

Reinforcement learning (RL) has achieved remarkable success in complex robotic systems (eg. quadruped locomotion). In previous works, the RL-based controller was typically implemented as a single neural network with concatenated observation input. However, the corresponding learned policy is highly task-specific. Since all motors are controlled in a centralized way, out-of-distribution local observations can impact global motors through the single coupled neural network policy. In contrast, animals and humans can control their limbs separately. Inspired by this biological phenomenon, we propose a Decentralized motor skill (DEMOS) learning algorithm to automatically discover motor groups that can be decoupled from each other while preserving essential connections and then learn a decentralized motor control policy. Our method improves the robustness and generalization of the policy without sacrificing performance. Experiments on quadruped and humanoid robots demonstrate that the learned policy is robust against local motor malfunctions and can be transferred to new tasks.

Reinforcement Learning (RL) algorithms have shown tremendous success in simulation environments, but their application to real-world problems faces significant challenges, with safety being a major concern. In particular, enforcing state-wise constraints is essential for many challenging tasks such as autonomous driving and robot manipulation. However, existing safe RL algorithms under the framework of Constrained Markov Decision Process (CMDP) do not consider state-wise constraints. To address this gap, we propose State-wise Constrained Policy Optimization (SCPO), the first general-purpose policy search algorithm for state-wise constrained reinforcement learning. SCPO provides guarantees for state-wise constraint satisfaction in expectation. In particular, we introduce the framework of Maximum Markov Decision Process, and prove that the worst-case safety violation is bounded under SCPO. We demonstrate the effectiveness of our approach on training neural network policies for extensive robot locomotion tasks, where the agent must satisfy a variety of state-wise safety constraints. Our results show that SCPO significantly outperforms existing methods and can handle state-wise constraints in high-dimensional robotics tasks.

Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do not generalize across labs), and we lack internet-scale robotics data. We take on these challenges via a new benchmark: Train Offline, Test Online (TOTO). TOTO provides remote users with access to shared robotic hardware for evaluating methods on common tasks and an open-source dataset of these tasks for offline training. Its manipulation task suite requires challenging generalization to unseen objects, positions, and lighting. We present initial results on TOTO comparing five pretrained visual representations and four offline policy learning baselines, remotely contributed by five institutions. The real promise of TOTO, however, lies in the future: we release the benchmark for additional submissions from any user, enabling easy, direct comparison to several methods without the need to obtain hardware or collect data.

Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable. Recently, safe RL (i.e., constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints. Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.

Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction. State-wise constraints are one of the most common constraints in real-world applications and one of the most challenging constraints in Safe RL. Enforcing state-wise constraints is necessary and essential to many challenging tasks such as autonomous driving, robot manipulation. This paper provides a comprehensive review of existing approaches that address state-wise constraints in RL. Under the framework of State-wise Constrained Markov Decision Process (SCMDP), we will discuss the connections, differences, and trade-offs of existing approaches in terms of (i) safety guarantee and scalability, (ii) safety and reward performance, and (iii) safety after convergence and during training. We also summarize limitations of current methods and discuss potential future directions.

Deep Reinforcement Learning (Deep RL) and Evolutionary Algorithms (EA) are two major paradigms of policy optimization with distinct learning principles, i.e., gradient-based v.s. gradient-free. An appealing research direction is integrating Deep RL and EA to devise new methods by fusing their complementary advantages. However, existing works on combining Deep RL and EA have two common drawbacks: 1) the RL agent and EA agents learn their policies individually, neglecting efficient sharing of useful common knowledge; 2) parameter-level policy optimization guarantees no semantic level of behavior evolution for the EA side. In this paper, we propose Evolutionary Reinforcement Learning with Two-scale State Representation and Policy Representation (ERL-Re$^2$), a novel solution to the aforementioned two drawbacks. The key idea of ERL-Re$^2$ is two-scale representation: all EA and RL policies share the same nonlinear state representation while maintaining individual} linear policy representations. The state representation conveys expressive common features of the environment learned by all the agents collectively; the linear policy representation provides a favorable space for efficient policy optimization, where novel behavior-level crossover and mutation operations can be performed. Moreover, the linear policy representation allows convenient generalization of policy fitness with the help of the Policy-extended Value Function Approximator (PeVFA), further improving the sample efficiency of fitness estimation. The experiments on a range of continuous control tasks show that ERL-Re$^2$ consistently outperforms advanced baselines and achieves the State Of The Art (SOTA). Our code is available on https://github.com/yeshenpy/ERL-Re2.

Explainability plays an increasingly important role in machine learning. Furthermore, humans view the world through a causal lens and thus prefer causal explanations over associational ones. Therefore, in this paper, we develop a causal explanation mechanism that quantifies the causal importance of states on actions and such importance over time. We also demonstrate the advantages of our mechanism over state-of-the-art associational methods in terms of RL policy explanation through a series of simulation studies, including crop irrigation, Blackjack, collision avoidance, and lunar lander.

Despite its importance in both industrial and service robotics, mobile manipulation remains a significant challenge as it requires a seamless integration of end-effector trajectory generation with navigation skills as well as reasoning over long-horizons. Existing methods struggle to control the large configuration space, and to navigate dynamic and unknown environments. In previous work, we proposed to decompose mobile manipulation tasks into a simplified motion generator for the end-effector in task space and a trained reinforcement learning agent for the mobile base to account for kinematic feasibility of the motion. In this work, we introduce Neural Navigation for Mobile Manipulation (N$^2$M$^2$) which extends this decomposition to complex obstacle environments and enables it to tackle a broad range of tasks in real world settings. The resulting approach can perform unseen, long-horizon tasks in unexplored environments while instantly reacting to dynamic obstacles and environmental changes. At the same time, it provides a simple way to define new mobile manipulation tasks. We demonstrate the capabilities of our proposed approach in extensive simulation and real-world experiments on multiple kinematically diverse mobile manipulators. Code and videos are publicly available at http://mobile-rl.cs.uni-freiburg.de.