Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning, and unsupervised learning provides a useful paradigm for autonomous acquisition of task-agnostic knowledge. In supervised settings, representations discovered through unsupervised pre-training offer important benefits when transferred to downstream tasks. Given the nature of the reinforcement learning problem, we argue that representation alone is not enough for efficient transfer in challenging domains and explore how to transfer knowledge through behavior. The behavior of pre-trained policies may be used for solving the task at hand (exploitation), as well as for collecting useful data to solve the problem (exploration). We argue that policies pre-trained to maximize coverage will produce behavior that is useful for both strategies. When using these policies for both exploitation and exploration, our agents discover better solutions. The largest gains are generally observed in domains requiring structured exploration, including settings where the behavior of the pre-trained policies is misaligned with the downstream task.

Reward decomposition is a critical problem in centralized training with decentralized execution (CTDE) paradigm for multi-agent reinforcement learning. To take full advantage of global information, which exploits the states from all agents and the related environment for decomposing Q values into individual credits, we propose a general meta-learning-based Mixing Network with Meta Policy Gradient (MNMPG) framework to distill the global hierarchy for delicate reward decomposition. The excitation signal for learning global hierarchy is deduced from the episode reward difference between before and after "exercise updates" through the utility network. Our method is generally applicable to the CTDE method using a monotonic mixing network. Experiments on the StarCraft II micromanagement benchmark demonstrate that our method just with a simple utility network is able to outperform the current state-of-the-art MARL algorithms on 4 of 5 super hard scenarios. Better performance can be further achieved when combined with a role-based utility network.

In recent years, trends towards studying object-based games have gained momentum in the fields of artificial intelligence, cognitive science, psychology, and neuroscience. In artificial intelligence, interactive physical games are now a common testbed for reinforcement learning (François-Lavet et al., 2018; Leike et al., 2017; Mnih et al., 2013; Sutton and Barto, 2018) and object representations are of particular interest for sample efficient and generalizable AI (Battaglia et al., 2018; Greff et al., 2020; van Steenkiste et al., 2019). In cognitive science and psychology, object-based games are used to study a variety of cognitive capacities, such as planning, intuitive physics, and intuitive psychology (Chabris, 2017; Ullman et al., 2017). Developmental psychologists also use object-based visual stimuli to probe questions about object-oriented reasoning in infants and young animals (Spelke and Kinzler, 2007; Wood et al., 2020). In neuroscience, object-based computer games have recently been used to study decision-making and physical reasoning in both human and non-human primates (Fischer et al., 2016; McDonald et al., 2019; Rajalingham et al., 2021; Yoo et al., 2020). Furthermore, a growing number of researchers are studying tasks using a combination of approaches from these fields.

Learning composable policies for environments with complex rules and tasks is a challenging problem. We introduce a hierarchical reinforcement learning framework called the Logical Options Framework (LOF) that learns policies that are satisfying, optimal, and composable. LOF efficiently learns policies that satisfy tasks by representing the task as an automaton and integrating it into learning and planning. We provide and prove conditions under which LOF will learn satisfying, optimal policies. And lastly, we show how LOF's learned policies can be composed to satisfy unseen tasks with only 10-50 retraining steps. We evaluate LOF on four tasks in discrete and continuous domains, including a 3D pick-and-place environment.

We study reinforcement learning (RL) with no-reward demonstrations, a setting in which an RL agent has access to additional data from the interaction of other agents with the same environment. However, it has no access to the rewards or goals of these agents, and their objectives and levels of expertise may vary widely. These assumptions are common in multi-agent settings, such as autonomous driving. To effectively use this data, we turn to the framework of successor features. This allows us to disentangle shared features and dynamics of the environment from agent-specific rewards and policies. We propose a multi-task inverse reinforcement learning (IRL) algorithm, called \emph{inverse temporal difference learning} (ITD), that learns shared state features, alongside per-agent successor features and preference vectors, purely from demonstrations without reward labels. We further show how to seamlessly integrate ITD with learning from online environment interactions, arriving at a novel algorithm for reinforcement learning with demonstrations, called $\Psi \Phi$-learning (pronounced `Sci-Fi'). We provide empirical evidence for the effectiveness of $\Psi \Phi$-learning as a method for improving RL, IRL, imitation, and few-shot transfer, and derive worst-case bounds for its performance in zero-shot transfer to new tasks.

Communication is a important factor that enables agents work cooperatively in multi-agent reinforcement learning (MARL). Most previous work uses continuous message communication whose high representational capacity comes at the expense of interpretability. Allowing agents to learn their own discrete message communication protocol emerged from a variety of domains can increase the interpretability for human designers and other agents.This paper proposes a method to generate discrete messages analogous to human languages, and achieve communication by a broadcast-and-listen mechanism based on self-attention. We show that discrete message communication has performance comparable to continuous message communication but with much a much smaller vocabulary size.Furthermore, we propose an approach that allows humans to interactively send discrete messages to agents.

ABSTRACT This research proposes a new integrated framework for identifying safe landing locations and planning in-flight divert maneuvers. The state-of-the-art algorithms for landing zone selection utilize local terrain features such as slopes and roughness to judge the safety and priority of the landing point. However, when there are additional chances of observation and diverting in the future, these algorithms are not able to evaluate the safety of the decision itself to target the selected landing point considering the overall descent trajectory. In response to this challenge, we propose a reinforcement learning framework that optimizes a landing site selection strategy concurrently with a guidance and control strategy to the target landing site. The trained agent could evaluate and select landing sites with explicit consideration of the terrain features, quality of future observations, and control to achieve a safe and efficient landing trajectory at a system-level. The proposed framework was able to achieve 94.8 % of successful landing in highly challenging landing sites where over 80% of the area around the initial target lading point is hazardous, by effectively updating the target landing site and feedback control gain during descent. INTRODUCTION On-board hazard detection and avoidance (HDA) capabilities are essential to enable new mission concepts that involve planetary surface operations. With a quick assessment of the perceived terrain data (e.g., DEM, visible spectrum map, or a combination thereof) from optical and/or LIDAR sensors, the HDA technology creates a map of probability of safety for prioritizing candidate landing zones. This paper is an updated version of Paper AAS 20-583 presented at the AAS/AIAA Astrodynamics Specialist Conference, Online, in 2020.

A promising characteristic of Deep Reinforcement Learning (DRL) is its capability to learn optimal policy in an end-to-end manner without relying on feature engineering. However, most approaches assume a fully observable state space, i.e. fully observable Markov Decision Process (MDP). In real-world robotics, this assumption is unpractical, because of the sensor issues such as sensors' capacity limitation and sensor noise, and the lack of knowledge about if the observation design is complete or not. These scenarios lead to Partially Observable MDP (POMDP) and need special treatment. In this paper, we propose Long-Short-Term-Memory-based Twin Delayed Deep Deterministic Policy Gradient (LSTM-TD3) by introducing a memory component to TD3, and compare its performance with other DRL algorithms in both MDPs and POMDPs. Our results demonstrate the significant advantages of the memory component in addressing POMDPs, including the ability to handle missing and noisy observation data.

Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments. Unlike cooperative environments where agents strive towards a common goal, mixed environments are notorious for the conflicts of selfish and social interests. As a consequence, purely rational agents often struggle to achieve and maintain cooperation. A prevalent approach to induce cooperative behaviour is to assign additional rewards based on other agents' well-being. However, this approach suffers from the issue of multi-agent credit assignment, which can hinder performance. This issue is efficiently alleviated in cooperative setting with such state-of-the-art algorithms as QMIX and COMA. Still, when applied to mixed environments, these algorithms may result in unfair allocation of rewards. We propose BAROCCO, an extension of these algorithms capable to balance individual and social incentives. The mechanism behind BAROCCO is to train two distinct but interwoven components that jointly affect each agent's decisions. Our meta-algorithm is compatible with both Q-learning and Actor-Critic frameworks. We experimentally confirm the advantages over the existing methods and explore the behavioural aspects of BAROCCO in two mixed multi-agent setups.

This paper develops an inherently parallelised, fast, approximate learning-based solution to the generic class of Capacitated Vehicle Routing with Time Windows and Dynamic Routing (CVRP-TWDR). Considering vehicles in a fleet as decentralised agents, we postulate that using reinforcement learning (RL) based adaptation is a key enabler for real-time route formation in a dynamic environment. The methodology allows each agent (vehicle) to independently evaluate the value of serving each customer, and uses a centralised allocation heuristic to finalise the allocations based on the generated values. We show that the solutions produced by this method on standard datasets are significantly faster than exact formulations and state-of-the-art meta-heuristics, while being reasonably close to optimal in terms of solution quality. We describe experiments in both the static case (when all customer demands and time windows are known in advance) as well as the dynamic case (where customers can `pop up' at any time during execution). The results with a single trained model on large, out-of-distribution test data demonstrate the scalability and flexibility of the proposed approach.