Deep reinforcement learning has achieved significant success in many decision-making tasks in various fields. However, it requires a large training time of dense neural networks to obtain a good performance. This hinders its applicability on low-resource devices where memory and computation are strictly constrained. In a step towards enabling deep reinforcement learning agents to be applied to low-resource devices, in this work, we propose for the first time to dynamically train deep reinforcement learning agents with sparse neural networks from scratch. We adopt the evolution principles of dynamic sparse training in the reinforcement learning paradigm and introduce a training algorithm that optimizes the sparse topology and the weight values jointly to dynamically fit the incoming data. Our approach is easy to be integrated into existing deep reinforcement learning algorithms and has many favorable advantages. First, it allows for significant compression of the network size which reduces the memory and computation costs substantially. This would accelerate not only the agent inference but also its training process. Second, it speeds up the agent learning process and allows for reducing the number of required training steps. Third, it can achieve higher performance than training the dense counterpart network. We evaluate our approach on OpenAI gym continuous control tasks. The experimental results show the effectiveness of our approach in achieving higher performance than one of the state-of-art baselines with a 50\% reduction in the network size and floating-point operations (FLOPs). Moreover, our proposed approach can reach the same performance achieved by the dense network with a 40-50\% reduction in the number of training steps.

Medical image segmentation is one of the important tasks of computer-aided diagnosis in medical image analysis. Since most medical images have the characteristics of blurred boundaries and uneven intensity distribution, through existing segmentation methods, the discontinuity within the target area and the discontinuity of the target boundary are likely to lead to rough or even erroneous boundary delineation. In this paper, we propose a new iterative refined interactive segmentation method for medical images based on agent reinforcement learning, which focuses on the problem of target segmentation boundaries. We model the dynamic process of drawing the target contour in a certain order as a Markov Decision Process (MDP) based on a deep reinforcement learning method. In the dynamic process of continuous interaction between the agent and the image, the agent tracks the boundary point by point in order within a limited length range until the contour of the target is completely drawn. In this process, the agent can quickly improve the segmentation performance by exploring an interactive policy in the image. The method we proposed is simple and effective. At the same time, we evaluate our method on the cardiac MRI scan data set. Experimental results show that our method has a better segmentation effect on the left ventricle in a small number of medical image data sets, especially in terms of segmentation boundaries, this method is better than existing methods. Based on our proposed method, the dynamic generation process of the predicted contour trajectory of the left ventricle will be displayed online at https://github.com/H1997ym/LV-contour-trajectory.

We developed Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention Network (sGAT) that leverages self-attention over both node and edge attributes as well as encoding spatial structure -- this capability is of considerable interest in areas such as molecular and synthetic biology and drug discovery. An attentional policy network is then introduced to learn decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with enhanced stability. Exploration is efficiently encouraged by incorporating innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while increasing the diversity of proposed molecules and reducing the complexity of paths to chemical synthesis.

We study objective robustness failures, a type of out-of-distribution robustness failure in reinforcement learning (RL). Objective robustness failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong objective. This kind of failure presents different risks than the robustness problems usually considered in the literature, since it involves agents that leverage their capabilities to pursue the wrong objective rather than simply failing to do anything useful. We provide the first explicit empirical demonstrations of objective robustness failures and present a partial characterization of its causes.

The fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state representation, and such representations are not guaranteed to preserve the Markov property. We introduce a novel set of conditions and prove that they are sufficient for learning a Markov abstract state representation. We then describe a practical training procedure that combines inverse model estimation and temporal contrastive learning to learn an abstraction that approximately satisfies these conditions. Our novel training objective is compatible with both online and offline training: it does not require a reward signal, but agents can capitalize on reward information when available. We empirically evaluate our approach on a visual gridworld domain and a set of continuous control benchmarks. Our approach learns representations that capture the underlying structure of the domain and lead to improved sample efficiency over state-of-the-art deep reinforcement learning with visual features -- often matching or exceeding the performance achieved with hand-designed compact state information.

The virtuoso plays the piano with passion, poetry and extraordinary technical ability. As Liszt said (a virtuoso)must call up scent and blossom, and breathe the breath of life. The strongest robots that can play a piano are based on a combination of specialized robot hands/piano and hardcoded planning algorithms. In contrast to that, in this paper, we demonstrate how an agent can learn directly from machine-readable music score to play the piano with dexterous hands on a simulated piano using reinforcement learning (RL) from scratch. We demonstrate the RL agents can not only find the correct key position but also deal with various rhythmic, volume and fingering, requirements. We achieve this by using a touch-augmented reward and a novel curriculum of tasks. We conclude by carefully studying the important aspects to enable such learning algorithms and that can potentially shed light on future research in this direction.

This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. In their decades-long chase to create artificial intelligence, computer scientists have designed and developed all kinds of complicated mechanisms and technologies to replicate vision, language, reasoning, motor skills, and other abilities associated with intelligent life. While these efforts have resulted in AI systems that can efficiently solve specific problems in limited environments, they fall short of developing the kind of general intelligence seen in humans and animals. In a new paper submitted to the peer-reviewed Artificial Intelligence journal, scientists at UK-based AI lab DeepMind argue that intelligence and its associated abilities will emerge not from formulating and solving complicated problems but by sticking to a simple but powerful principle: reward maximization. Titled "Reward is Enough," the paper, which is still in pre-proof as of this writing, draws inspiration from studying the evolution of natural intelligence as well as drawing lessons from recent achievements in artificial intelligence.

Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids, i.e., the wining price is fixed, leading to poor performance of the derived solution. Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose. (2) Previous works cannot well handle the underlying complex bidding environment, leading to poor model convergence. This problem could be amplified when handling multiple objectives of advertisers which are practical demands but not considered by previous work. In this paper, we propose a novel multi-objective cooperative bid optimization formulation called Multi-Agent Cooperative bidding Games (MACG). MACG sets up a carefully designed multi-objective optimization framework where different objectives of advertisers are incorporated. A global objective to maximize the overall profit of all advertisements is added in order to encourage better cooperation and also to protect self-bidding advertisers. To avoid collusion, we also introduce an extra platform revenue constraint. We analyze the optimal functional form of the bidding formula theoretically and design a policy network accordingly to generate auction-level bids. Then we design an efficient multi-agent evolutionary strategy for model optimization. Offline experiments and online A/B tests conducted on the Taobao platform indicate both single advertiser's objective and global profit have been significantly improved compared to state-of-art methods.

A major driver behind the success of modern machine learning algorithms has been their ability to process ever-larger amounts of data. As a result, the use of distributed systems in both research and production has become increasingly prevalent as a means to scale to this growing data. At the same time, however, distributing the learning process can drastically complicate the implementation of even simple algorithms. This is especially problematic as many machine learning practitioners are not well-versed in the design of distributed systems, let alone those that have complicated communication topologies. In this work we introduce Launchpad, a programming model that simplifies the process of defining and launching distributed systems that is specifically tailored towards a machine learning audience. We describe our framework, its design philosophy and implementation, and give a number of examples of common learning algorithms whose designs are greatly simplified by this approach.

Machine learning algorithms often make decisions on behalf of agents with varied and sometimes conflicting interests. In domains where agents can choose to take their own action or delegate their action to a central mediator, an open question is how mediators should take actions on behalf of delegating agents. The main existing approach uses delegating agents to punish non-delegating agents in an attempt to get all agents to delegate, which tends to be costly for all. We introduce a Pareto Mediator which aims to improve outcomes for delegating agents without making any of them worse off. Our experiments in random normal form games, a restaurant recommendation game, and a reinforcement learning sequential social dilemma show that the Pareto Mediator greatly increases social welfare. Also, even when the Pareto Mediator is based on an incorrect model of agent utility, performance gracefully degrades to the pre-intervention level, due to the individual autonomy preserved by the voluntary mediator.