Intelligent behaviour in the physical world exhibits structure at multiple spatial and temporal scales. Although movements are ultimately executed at the level of instantaneous muscle tensions or joint torques, they must be selected to serve goals defined on much longer timescales, and in terms of relations that extend far beyond the body itself, ultimately involving coordination with other agents. Recent research in artificial intelligence has shown the promise of learning-based approaches to the respective problems of complex movement, longer-term planning and multi-agent coordination. However, there is limited research aimed at their integration. We study this problem by training teams of physically simulated humanoid avatars to play football in a realistic virtual environment. We develop a method that combines imitation learning, single- and multi-agent reinforcement learning and population-based training, and makes use of transferable representations of behaviour for decision making at different levels of abstraction. In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds. We investigate the emergence of behaviours at different levels of abstraction, as well as the representations that underlie these behaviours using several analysis techniques, including statistics from real-world sports analytics. Our work constitutes a complete demonstration of integrated decision-making at multiple scales in a physically embodied multi-agent setting. See project video at https://youtu.be/KHMwq9pv7mg.

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framework. Our algorithm can be interpreted as a natural extension of work on KL-regularized RL and introduces a form of tree search for continuous action spaces. We demonstrate that additional computation spent on model-based policy improvement during learning can improve data efficiency, and confirm that model-based policy improvement during action selection can also be beneficial. Quantitatively, our algorithm improves data efficiency on several continuous control benchmarks (when a model is learned in parallel), and it provides significant improvements in wall-clock time in high-dimensional domains (when a ground truth model is available). The unified framework also helps us to better understand the space of model-based and model-free algorithms. In particular, we demonstrate that some benefits attributed to model-based RL can be obtained without a model, simply by utilizing more computation.

Solutions to most complex tasks can be decomposed into simpler, intermediate skills, reusable across wider ranges of problems. We follow this concept and introduce Hindsight Off-policy Options (HO2), a new algorithm for efficient and robust option learning. The algorithm relies on critic-weighted maximum likelihood estimation and an efficient dynamic programming inference procedure over off-policy trajectories. We can backpropagate through the inference procedure through time and the policy components for every time-step, making it possible to train all component's parameters off-policy, independently of the data-generating behavior policy. Experimentally, we demonstrate that HO2 outperforms competitive baselines and solves demanding robot stacking and ball-in-cup tasks from raw pixel inputs in simulation. We further compare autoregressive option policies with simple mixture policies, providing insights into the relative impact of two types of abstractions common in the options framework: action abstraction and temporal abstraction. Finally, we illustrate challenges caused by stale data in off-policy options learning and provide effective solutions.

Deep reinforcement learning has led to many recent-and groundbreaking-advancements. However, these advances have often come at the cost of both the scale and complexity of the underlying RL algorithms. Increases in complexity have in turn made it more difficult for researchers to reproduce published RL algorithms or rapidly prototype ideas. To address this, we introduce Acme, a tool to simplify the development of novel RL algorithms that is specifically designed to enable simple agent implementations that can be run at various scales of execution. Our aim is also to make the results of various RL algorithms developed in academia and industrial labs easier to reproduce and extend. To this end we are releasing baseline implementations of various algorithms, created using our framework. In this work we introduce the major design decisions behind Acme and show how these are used to construct these baselines. We also experiment with these agents at different scales of both complexity and computation-including distributed versions. Ultimately, we show that the design decisions behind Acme lead to agents that can be scaled both up and down and that, for the most part, greater levels of parallelization result in agents with equivalent performance, just faster.

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over objectives in their native units. In this paper we propose a novel algorithm for multi-objective reinforcement learning that enables setting desired preferences for objectives in a scale-invariant way. We propose to learn an action distribution for each objective, and we use supervised learning to fit a parametric policy to a combination of these distributions. We demonstrate the effectiveness of our approach on challenging high-dimensional real and simulated robotics tasks, and show that setting different preferences in our framework allows us to trace out the space of nondominated solutions.

Stochastic search algorithms are general black-box optimizers. Due to their ease of use and their generality, they have recently also gained a lot of attention in operations research, machine learning and policy search. Yet, these algorithms require a lot of evaluations of the objective, scale poorly with the problem dimension, are affected by highly noisy objective functions and may converge prematurely. To alleviate these problems, we introduce a new surrogate-based stochastic search approach. We learn simple, quadratic surrogate models of the objective function.

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper, we explore how model-based Reinforcement Learning (RL) can facilitate transfer to new tasks. We develop an algorithm that learns an action-conditional, predictive model of expected future observations, rewards and values from which a policy can be derived by following the gradient of the estimated value along imagined trajectories. We show how robust policy optimization can be achieved in robot manipulation tasks even with approximate models that are learned directly from vision and proprioception. We evaluate the efficacy of our approach in a transfer learning scenario, re-using previously learned models on tasks with different reward structures and visual distractors, and show a significant improvement in learning speed compared to strong off-policy baselines. Videos with results can be found at https://sites.google.com/view/ivg-corl19

Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimensionality of systems of equations. In supervised learning, such as in image classification tasks, rotation, translation and scale invariances are used to augment training datasets. In this work, we use data augmentation in a similar way, exploiting symmetry in the quadruped domain of the DeepMind control suite (Tassa et al. 2018) to add to the trajectories experienced by the actor in the actor-critic algorithm of Abdolmaleki et al. (2018). In a data-limited regime, the agent using a set of experiences augmented through symmetry is able to learn faster. Our approach can be used to inject knowledge of invariances in the domain and task to augment learning in robots, and more generally, to speed up learning in realistic robotics applications.

Some of the most successful applications of deep reinforcement learning to challenging domains in discrete and continuous control have used policy gradient methods in the on-policy setting. However, policy gradients can suffer from large variance that may limit performance, and in practice require carefully tuned entropy regularization to prevent policy collapse. As an alternative to policy gradient algorithms, we introduce V-MPO, an on-policy adaptation of Maximum a Posteriori Policy Optimization (MPO) that performs policy iteration based on a learned state-value function. We show that V-MPO surpasses previously reported scores for both the Atari-57 and DMLab-30 benchmark suites in the multi-task setting, and does so reliably without importance weighting, entropy regularization, or population-based tuning of hyperparameters. On individual DMLab and Atari levels, the proposed algorithm can achieve scores that are substantially higher than has previously been reported. V-MPO is also applicable to problems with high-dimensional, continuous action spaces, which we demonstrate in the context of learning to control simulated humanoids with 22 degrees of freedom from full state observations and 56 degrees of freedom from pixel observations, as well as example OpenAI Gym tasks where V-MPO achieves substantially higher asymptotic scores than previously reported.

The successful application of flexible, general learning algorithms -- such as deep reinforcement learning -- to real-world robotics applications is often limited by their poor data-efficiency. Domains with more than a single dominant task of interest encourage algorithms that share partial solutions across tasks to limit the required experiment time. We develop and investigate simple hierarchical inductive biases -- in the form of structured policies -- as a mechanism for knowledge transfer across tasks in reinforcement learning (RL). To leverage the power of these structured policies we design an RL algorithm that enables stable and fast learning. We demonstrate the success of our method both in simulated robot environments (using locomotion and manipulation domains) as well as real robot experiments, demonstrating substantially better data-efficiency than competitive baselines.