Defining and thereby separating the intelligent "agent" from its embodied "environment", which then provides feedback to the agent, is crucial to model intelligent behaviour. Popular approaches, like reinforcement learning (RL), heavily employ such models containing agent-environment loops, which boils down the problem to agent(s) trying to maximise reward in the given uncertain environment Sutton and Barto [2018]. Active inference has emerged in neuroscience as a biologically plausible framework Friston [2010], which adopts a different approach to modelling intelligent behaviour compared to other contemporary methods like RL. In the active inference framework, an agent accumulates and maximises the model evidence during its lifetime to perceive, learn, and make decisions Da Costa et al. [2020], Sajid et al. [2021], Millidge et al. [2020]. However, maximising the model evidence becomes challenging when the agent encounters a highly'entropic' observation (i.e. an unexpected observation) concerning the agent's generative (world) model Da Costa et al. [2020], Sajid et al. [2021], Millidge et al. [2020]. This seemingly intractable objective of maximising model evidence (or minimising the entropy of encountered observations) is achievable by minimising an upper bound on the entropy of observations, called variational free energy Da Costa et al. [2020], Sajid et al. [2021]. Given this general foundation, active inference Friston et al. [2017] offers excellent flexibility in defining the generative model structure for a given problem and has attracted much attention in various domainsKuchling et al. [2020], Deane et al. [2020]. In this work, we develop an efficient decision-making scheme based on active inference by combining'planning' and'learning from experience'.

Designing a humanoid locomotion controller is challenging and classically split up in sub-problems. Footstep planning is one of those, where the sequence of footsteps is defined. Even in simpler environments, finding a minimal sequence, or even a feasible sequence, yields a complex optimization problem. In the literature, this problem is usually addressed by search-based algorithms (e.g. variants of A*). However, such approaches are either computationally expensive or rely on hand-crafted tuning of several parameters. In this work, at first, we propose an efficient footstep planning method to navigate in local environments with obstacles, based on state-of-the art Deep Reinforcement Learning (DRL) techniques, with very low computational requirements for on-line inference. Our approach is heuristic-free and relies on a continuous set of actions to generate feasible footsteps. In contrast, other methods necessitate the selection of a relevant discrete set of actions. Second, we propose a forecasting method, allowing to quickly estimate the number of footsteps required to reach different candidates of local targets. This approach relies on inherent computations made by the actor-critic DRL architecture. We demonstrate the validity of our approach with simulation results, and by a deployment on a kid-size humanoid robot during the RoboCup 2023 competition.

The evolution and growing automation of collaborative robots introduce more complexity and unpredictability to systems, highlighting the crucial need for robot's adaptability and flexibility to address the increasing complexities of their environment. In typical industrial production scenarios, robots are often required to be re-programmed when facing a more demanding task or even a few changes in workspace conditions. To increase productivity, efficiency and reduce human effort in the design process, this paper explores the potential of using digital twin combined with Reinforcement Learning (RL) to enable robots to generate self-improving collision-free trajectories in real time. The digital twin, acting as a virtual counterpart of the physical system, serves as a 'forward run' for monitoring, controlling, and optimizing the physical system in a safe and cost-effective manner. The physical system sends data to synchronize the digital system through the video feeds from cameras, which allows the virtual robot to update its observation and policy based on real scenarios. The bidirectional communication between digital and physical systems provides a promising platform for hardware-in-the-loop RL training through trial and error until the robot successfully adapts to its new environment. The proposed online training framework is demonstrated on the Unfactory Xarm5 collaborative robot, where the robot end-effector aims to reach the target position while avoiding obstacles. The experiment suggest that proposed framework is capable of performing policy online training, and that there remains significant room for improvement.

Existing multi-agent coordination techniques are often fragile and vulnerable to anomalies such as agent attrition and communication disturbances, which are quite common in the real-world deployment of systems like field robotics. To better prepare these systems for the real world, we present a graph neural network (GNN)-based multi-agent reinforcement learning (MARL) method for resilient distributed coordination of a multi-robot system. Our method, Multi-Agent Graph Embedding-based Coordination (MAGEC), is trained using multi-agent proximal policy optimization (PPO) and enables distributed coordination around global objectives under agent attrition, partial observability, and limited or disturbed communications. We use a multi-robot patrolling scenario to demonstrate our MAGEC method in a ROS 2-based simulator and then compare its performance with prior coordination approaches. Results demonstrate that MAGEC outperforms existing methods in several experiments involving agent attrition and communication disturbance, and provides competitive results in scenarios without such anomalies.

The increasing integration of electric vehicles (EVs) into the grid can pose a significant risk to the distribution system operation in the absence of coordination. In response to the need for effective coordination of EVs within the distribution network, this paper presents a safety-aware reinforcement learning (RL) algorithm designed to manage EV charging stations while ensuring the satisfaction of system constraints. Unlike existing methods, our proposed algorithm does not rely on explicit penalties for constraint violations, eliminating the need for penalty coefficient tuning. Furthermore, managing EV charging stations is further complicated by multiple uncertainties, notably the variability in solar energy generation and energy prices. To address this challenge, we develop an off-policy RL algorithm to efficiently utilize data to learn patterns in such uncertain environments. Our algorithm also incorporates a maximum entropy framework to enhance the RL algorithm's exploratory process, preventing convergence to local optimal solutions. Simulation results demonstrate that our algorithm outperforms traditional RL algorithms in managing EV charging in the distribution network.

Robot arms should be able to learn new tasks. One framework here is reinforcement learning, where the robot is given a reward function that encodes the task, and the robot autonomously learns actions to maximize its reward. Existing approaches to reinforcement learning often frame this problem as a Markov decision process, and learn a policy (or a hierarchy of policies) to complete the task. These policies reason over hundreds of fine-grained actions that the robot arm needs to take: e.g., moving slightly to the right or rotating the end-effector a few degrees. But the manipulation tasks that we want robots to perform can often be broken down into a small number of high-level motions: e.g., reaching an object or turning a handle. In this paper we therefore propose a waypoint-based approach for model-free reinforcement learning. Instead of learning a low-level policy, the robot now learns a trajectory of waypoints, and then interpolates between those waypoints using existing controllers. Our key novelty is framing this waypoint-based setting as a sequence of multi-armed bandits: each bandit problem corresponds to one waypoint along the robot's motion. We theoretically show that an ideal solution to this reformulation has lower regret bounds than standard frameworks. We also introduce an approximate posterior sampling solution that builds the robot's motion one waypoint at a time. Results across benchmark simulations and two real-world experiments suggest that this proposed approach learns new tasks more quickly than state-of-the-art baselines. See videos here: https://youtu.be/MMEd-lYfq4Y

In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance. However, ensuring that the deep RL policy and value networks are respectively equivariant and invariant to exploit these symmetries is a substantial challenge. Related works try to design networks that are equivariant and invariant by construction, limiting them to a very restricted library of components, which in turn hampers the expressiveness of the networks. This paper proposes a method to construct equivariant policies and invariant value functions without specialized neural network components, which we term equivariant ensembles. We further add a regularization term for adding inductive bias during training. In a map-based path planning case study, we show how equivariant ensembles and regularization benefit sample efficiency and performance.

For instance, TD3+Behavior Cloning (TD3+BC, Fujimoto and Gu, 2021) achieves this by regularizing the actor loss with the divergence between the learned policy and the data-generating policy, while Advantage Weighted Actor Critic (AWAC, Nair et al., 2020) seeks a policy maximizing the data likelihood weighted by its exponentiated advantage function. Later extensions of AWAC also modify the critic loss to avoid querying actions outside the given data by learning a value function, e.g., by expectile regression in Implicit Q-learning (IQL, Kostrikov et al., 2022) and Gumbel regression in Extreme Q-learning (XQL, Garg et al., 2023). This class of methods can be easily integrated with online fine-tuning, even leading to several successful applications for real-world tasks (Lu et al., 2022; Nair et al., 2023). However, current offline RL methods still fail in simple settings. Hong et al. (2023c,b) showed that if the data contains many low-return and few high-return trajectories, policy constrained methods are unnecessarily conservative and fail to learn good behavior. Singh et al. (2023) report a similar effect on heteroskedastic datasets where the variability of behaviors differs across different regions of the state space.

Efficiently learning equilibria with large state and action spaces in general-sum Markov games while overcoming the curse of multi-agency is a challenging problem. Recent works have attempted to solve this problem by employing independent linear function classes to approximate the marginal $Q$-value for each agent. However, existing sample complexity bounds under such a framework have a suboptimal dependency on the desired accuracy $\varepsilon$ or the action space. In this work, we introduce a new algorithm, Lin-Confident-FTRL, for learning coarse correlated equilibria (CCE) with local access to the simulator, i.e., one can interact with the underlying environment on the visited states. Up to a logarithmic dependence on the size of the state space, Lin-Confident-FTRL learns $\epsilon$-CCE with a provable optimal accuracy bound $O(\epsilon^{-2})$ and gets rids of the linear dependency on the action space, while scaling polynomially with relevant problem parameters (such as the number of agents and time horizon). Moreover, our analysis of Linear-Confident-FTRL generalizes the virtual policy iteration technique in the single-agent local planning literature, which yields a new computationally efficient algorithm with a tighter sample complexity bound when assuming random access to the simulator.

We present JaxUED, an open-source library providing minimal dependency implementations of modern Unsupervised Environment Design (UED) algorithms in Jax. JaxUED leverages hardware acceleration to obtain on the order of 100x speedups compared to prior, CPU-based implementations. Inspired by CleanRL, we provide fast, clear, understandable, and easily modifiable implementations, with the aim of accelerating research into UED. This paper describes our library and contains baseline results. Code can be found at https://github.com/DramaCow/jaxued.