Many existing reinforcement learning (RL) methods employ stochastic gradient iteration on the back end, whose stability hinges upon a hypothesis that the data-generating process mixes exponentially fast with a rate parameter that appears in the step-size selection. Unfortunately, this assumption is violated for large state spaces or settings with sparse rewards, and the mixing time is unknown, making the step size inoperable. In this work, we propose an RL methodology attuned to the mixing time by employing a multi-level Monte Carlo estimator for the critic, the actor, and the average reward embedded within an actor-critic (AC) algorithm. This method, which we call \textbf{M}ulti-level \textbf{A}ctor-\textbf{C}ritic (MAC), is developed especially for infinite-horizon average-reward settings and neither relies on oracle knowledge of the mixing time in its parameter selection nor assumes its exponential decay; it, therefore, is readily applicable to applications with slower mixing times. Nonetheless, it achieves a convergence rate comparable to the state-of-the-art AC algorithms. We experimentally show that these alleviated restrictions on the technical conditions required for stability translate to superior performance in practice for RL problems with sparse rewards.

The ability to leverage shared behaviors between tasks is critical for sample-efficient multi-task reinforcement learning (MTRL). While prior methods have primarily explored parameter and data sharing, direct behavior-sharing has been limited to task families requiring similar behaviors. Our goal is to extend the efficacy of behavior-sharing to more general task families that could require a mix of shareable and conflicting behaviors. Our key insight is an agent's behavior across tasks can be used for mutually beneficial exploration. To this end, we propose a simple MTRL framework for identifying shareable behaviors over tasks and incorporating them to guide exploration. We empirically demonstrate how behavior sharing improves sample efficiency and final performance on manipulation and navigation MTRL tasks and is even complementary to parameter sharing. Result videos are available at https://sites.google.com/view/qmp-mtrl.

We develop an extension of posterior sampling for reinforcement learning (PSRL) that is suited for a continuing agent-environment interface and integrates naturally into agent designs that scale to complex environments. The approach, continuing PSRL, maintains a statistically plausible model of the environment and follows a policy that maximizes expected $\gamma$-discounted return in that model. At each time, with probability $1-\gamma$, the model is replaced by a sample from the posterior distribution over environments. For a choice of discount factor that suitably depends on the horizon $T$, we establish an $\tilde{O}(\tau S \sqrt{A T})$ bound on the Bayesian regret, where $S$ is the number of environment states, $A$ is the number of actions, and $\tau$ denotes the reward averaging time, which is a bound on the duration required to accurately estimate the average reward of any policy. Our work is the first to formalize and rigorously analyze the resampling approach with randomized exploration.

There have been many recent advances in the field of artificial intelligence (AI), and it is difficult to summarize all of them in a single answer. We briefly touched on the great advancements inthe fields of NLP, computer vision and reinforcement learning. Natural language processing: Natural language processing (NLP) is a key technology for enabling AI systems to understand and generate human language, and there have been many recent advances in this area. Researchers have developed new techniques for language translation, summarisation, and dialogue generation that are more accurate and effective than previous methods. Computer vision: Computer vision is another important area of AI, and there have been many recent developments in this field.

Tracking an odour plume to locate its source under variable wind and plume statistics is a complex task. Flying insects routinely accomplish such tracking, often over long distances, in pursuit of food or mates. Several aspects of this remarkable behaviour and its underlying neural circuitry have been studied experimentally. Here we take a complementary in silico approach to develop an integrated understanding of their behaviour and neural computations. Specifically, we train artificial recurrent neural network agents using deep reinforcement learning to locate the source of simulated odour plumes that mimic features of plumes in a turbulent flow. Interestingly, the agents’ emergent behaviours resemble those of flying insects, and the recurrent neural networks learn to compute task-relevant variables with distinct dynamic structures in population activity. Our analyses put forward a testable behavioural hypothesis for tracking plumes in changing wind direction, and we provide key intuitions for memory requirements and neural dynamics in odour plume tracking. Olfactory navigation is a well-studied topic in insect behaviour, but many aspects of the challenging task of odour plume tracking are unknown. In a deep reinforcement learning approach, artificial agents are trained to produce (in silico) trajectories to localize the source of an odour plume, showing dynamics that mimic real insect behaviours.

The process of designing costmaps for off-road driving tasks is often a challenging and engineering-intensive task. Recent work in costmap design for off-road driving focuses on training deep neural networks to predict costmaps from sensory observations using corpora of expert driving data. However, such approaches are generally subject to over-confident mispredictions and are rarely evaluated in-the-loop on physical hardware. We present an inverse reinforcement learning-based method of efficiently training deep cost functions that are uncertainty-aware. We do so by leveraging recent advances in highly parallel model-predictive control and robotic risk estimation. In addition to demonstrating improvement at reproducing expert trajectories, we also evaluate the efficacy of these methods in challenging off-road navigation scenarios. We observe that our method significantly outperforms a geometric baseline, resulting in 44% improvement in expert path reconstruction and 57% fewer interventions in practice. We also observe that varying the risk tolerance of the vehicle results in qualitatively different navigation behaviors, especially with respect to higher-risk scenarios such as slopes and tall grass.

We introduce the Blackwell discount factor for Markov Decision Processes (MDPs). Classical objectives for MDPs include discounted, average, and Blackwell optimality. Many existing approaches to computing average-optimal policies solve for discounted optimal policies with a discount factor close to $1$, but they only work under strong or hard-to-verify assumptions such as ergodicity or weakly communicating MDPs. In this paper, we show that when the discount factor is larger than the Blackwell discount factor $\gamma_{\mathrm{bw}}$, all discounted optimal policies become Blackwell- and average-optimal, and we derive a general upper bound on $\gamma_{\mathrm{bw}}$. The upper bound on $\gamma_{\mathrm{bw}}$ provides the first reduction from average and Blackwell optimality to discounted optimality, without any assumptions, and new polynomial-time algorithms for average- and Blackwell-optimal policies. Our work brings new ideas from the study of polynomials and algebraic numbers to the analysis of MDPs. Our results also apply to robust MDPs, enabling the first algorithms to compute robust Blackwell-optimal policies.

The fifth generation (5G) of wireless networks is set out to meet the stringent requirements of vehicular use cases. Edge computing resources can aid in this direction by moving processing closer to end-users, reducing latency. However, given the stochastic nature of traffic loads and availability of physical resources, appropriate auto-scaling mechanisms need to be employed to support cost-efficient and performant services. To this end, we employ Deep Reinforcement Learning (DRL) for vertical scaling in Edge computing to support vehicular-to-network communications. We address the problem using Deep Deterministic Policy Gradient (DDPG). As DDPG is a model-free off-policy algorithm for learning continuous actions, we introduce a discretization approach to support discrete scaling actions. Thus we address scalability problems inherent to high-dimensional discrete action spaces. Employing a real-world vehicular trace data set, we show that DDPG outperforms existing solutions, reducing (at minimum) the average number of active CPUs by 23% while increasing the long-term reward by 24%.

Social dilemmas can be considered situations where individual rationality leads to collective irrationality. The multi-agent reinforcement learning community has leveraged ideas from social science, such as social value orientations (SVO), to solve social dilemmas in complex cooperative tasks. In this paper, by first introducing the typical "division of labor or roles" mechanism in human society, we provide a promising solution for intertemporal social dilemmas (ISD) with SVOs. A novel learning framework, called Learning Roles with Emergent SVOs (RESVO), is proposed to transform the learning of roles into the social value orientation emergence, which is symmetrically solved by endowing agents with altruism to share rewards with other agents. An SVO-based role embedding space is then constructed by individual conditioning policies on roles with a novel rank regularizer and mutual information maximizer. Experiments show that RESVO achieves a stable division of labor and cooperation in ISDs with different complexity.

From natural language processing to genome sequencing, large-scale machine learning models are bringing advances to a broad range of fields. Many of these models are too large to be trained on a single machine, and instead must be distributed across multiple devices. This has motivated the research of new compute and network systems capable of handling such tasks. In particular, recent work has focused on developing management schemes which decide how to allocate distributed resources such that some overall objective, such as minimising the job completion time (JCT), is optimised. However, such studies omit explicit consideration of how much a job should be distributed, usually assuming that maximum distribution is desirable. In this work, we show that maximum parallelisation is sub-optimal in relation to user-critical metrics such as throughput and blocking rate. To address this, we propose PAC-ML (partitioning for asynchronous computing with machine learning). PAC-ML leverages a graph neural network and reinforcement learning to learn how much to partition computation graphs such that the number of jobs which meet arbitrary user-defined JCT requirements is maximised. In experiments with five real deep learning computation graphs on a recently proposed optical architecture across four user-defined JCT requirement distributions, we demonstrate PAC-ML achieving up to 56.2% lower blocking rates in dynamic job arrival settings than the canonical maximum parallelisation strategy used by most prior works.