arXiv subjects

Paul Weng

Publications and source records attributed to Paul Weng.

At least 37 records · Page 2Linked to original sources

arXiv2022

A Survey on Interpretable Reinforcement Learning

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts, a learned policy needs for instance to be interpretable, so that it can be inspected before any deployment (e.g., for safety and verifiability reasons). This survey provides an overview of various approaches to achieve higher interpretability in reinforcement learning (RL). To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion. In particular, we argue that interpretable RL may embrace different facets: interpretable inputs, interpretable (transition/reward) models, and interpretable decision-making. Based on this scheme, we summarize and analyze recent work related to interpretable RL with an emphasis on papers published in the past 10 years. We also discuss briefly some related research areas and point to some potential promising research directions.

cs.LG↗

arXiv2021

Neuro-Symbolic Hierarchical Rule Induction

We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems. In this model, which is built from a set of meta-rules organised in a hierarchical structure, first-order rules are invented by learning embeddings to match facts and body predicates of a meta-rule. To instantiate it, we specifically design an expressive set of generic meta-rules, and demonstrate they generate a consequent fragment of Horn clauses. During training, we inject a controlled \pw{Gumbel} noise to avoid local optima and employ interpretability-regularization term to further guide the convergence to interpretable rules. We empirically validate our model on various tasks (ILP, visual genome, reinforcement learning) against several state-of-the-art methods.

cs.LG↗

arXiv2021

Generalization in Deep RL for TSP Problems via Equivariance and Local Search

Deep reinforcement learning (RL) has proved to be a competitive heuristic for solving small-sized instances of traveling salesman problems (TSP), but its performance on larger-sized instances is insufficient. Since training on large instances is impractical, we design a novel deep RL approach with a focus on generalizability. Our proposition consisting of a simple deep learning architecture that learns with novel RL training techniques, exploits two main ideas. First, we exploit equivariance to facilitate training. Second, we interleave efficient local search heuristics with the usual RL training to smooth the value landscape. In order to validate the whole approach, we empirically evaluate our proposition on random and realistic TSP problems against relevant state-of-the-art deep RL methods. Moreover, we present an ablation study to understand the contribution of each of its component

cs.LG↗

arXiv2021

Improving Generalization of Deep Reinforcement Learning-based TSP Solvers

Recent work applying deep reinforcement learning (DRL) to solve traveling salesman problems (TSP) has shown that DRL-based solvers can be fast and competitive with TSP heuristics for small instances, but do not generalize well to larger instances. In this work, we propose a novel approach named MAGIC that includes a deep learning architecture and a DRL training method. Our architecture, which integrates a multilayer perceptron, a graph neural network, and an attention model, defines a stochastic policy that sequentially generates a TSP solution. Our training method includes several innovations: (1) we interleave DRL policy gradient updates with local search (using a new local search technique), (2) we use a novel simple baseline, and (3) we apply curriculum learning. Finally, we empirically demonstrate that MAGIC is superior to other DRL-based methods on random TSP instances, both in terms of performance and generalizability. Moreover, our method compares favorably against TSP heuristics and other state-of-the-art approach in terms of performance and computational time.

cs.LG↗

arXiv2021

Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning

We consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL). We formalize it in a principled way as the problem of optimizing a welfare function that explicitly encodes two important aspects of fairness: efficiency and equity. As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness. In experiments, we demonstrate the importance of the two sub-networks for fair optimization. Our overall approach is general as it can accommodate any (sub)differentiable welfare function. Therefore, it is compatible with various notions of fairness that have been proposed in the literature (e.g., lexicographic maximin, generalized Gini social welfare function, proportional fairness). Our solution method is generic and can be implemented in various MARL settings: centralized training and decentralized execution, or fully decentralized. Finally, we experimentally validate our approach in various domains and show that it can perform much better than previous methods.

cs.LG↗

arXiv2021

Hyperparameter Auto-tuning in Self-Supervised Robotic Learning

Policy optimization in reinforcement learning requires the selection of numerous hyperparameters across different environments. Fixing them incorrectly may negatively impact optimization performance leading notably to insufficient or redundant learning. Insufficient learning (due to convergence to local optima) results in under-performing policies whilst redundant learning wastes time and resources. The effects are further exacerbated when using single policies to solve multi-task learning problems. Observing that the Evidence Lower Bound (ELBO) used in Variational Auto-Encoders correlates with the diversity of image samples, we propose an auto-tuning technique based on the ELBO for self-supervised reinforcement learning. Our approach can auto-tune three hyperparameters: the replay buffer size, the number of policy gradient updates during each epoch, and the number of exploration steps during each epoch. We use a state-of-the-art self-supervised robot learning framework (Reinforcement Learning with Imagined Goals (RIG) using Soft Actor-Critic) as baseline for experimental verification. Experiments show that our method can auto-tune online and yields the best performance at a fraction of the time and computational resources. Code, video, and appendix for simulated and real-robot experiments can be found at the project page \url{www.JuanRojas.net/autotune}.

cs.RO↗

arXiv2021

Learning Symbolic Rules for Interpretable Deep Reinforcement Learning

Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks. However, this black-box approach fails to explain the learned policy in a human understandable way. To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL. This framework features a fertilization of reasoning and learning modules, enabling end-to-end learning with prior symbolic knowledge. Moreover, interpretability is achieved by extracting the logical rules learned by the reasoning module in a symbolic rule space. The experimental results show that our framework has better interpretability, along with competing performance in comparison to state-of-the-art approaches.

cs.AI↗

arXiv2021

Safe Distributional Reinforcement Learning

Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting. Our general model accepts various definitions of safety(e.g., bounds on expected performance, CVaR, variance, or probability of reaching bad states). To ensure safety during learning, we extend a safe policy optimization method to solve our problem. The distributional RL perspective leads to a more efficient algorithm while additionally catering for natural safe constraints. We empirically validate our propositions on artificial and real domains against appropriate state-of-the-art safe RL algorithms.

cs.LG↗

arXiv2021

Analytics and Machine Learning in Vehicle Routing Research

The Vehicle Routing Problem (VRP) is one of the most intensively studied combinatorial optimisation problems for which numerous models and algorithms have been proposed. To tackle the complexities, uncertainties and dynamics involved in real-world VRP applications, Machine Learning (ML) methods have been used in combination with analytical approaches to enhance problem formulations and algorithmic performance across different problem solving scenarios. However, the relevant papers are scattered in several traditional research fields with very different, sometimes confusing, terminologies. This paper presents a first, comprehensive review of hybrid methods that combine analytical techniques with ML tools in addressing VRP problems. Specifically, we review the emerging research streams on ML-assisted VRP modelling and ML-assisted VRP optimisation. We conclude that ML can be beneficial in enhancing VRP modelling, and improving the performance of algorithms for both online and offline VRP optimisations. Finally, challenges and future opportunities of VRP research are discussed.

cs.LG↗

arXiv2020

Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards

As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the problem of learning a policy that treats its users equitably. In this paper, we formulate this novel RL problem, in which an objective function, which encodes a notion of fairness that we formally define, is optimized. For this problem, we provide a theoretical discussion where we examine the case of discounted rewards and that of average rewards. During this analysis, we notably derive a new result in the standard RL setting, which is of independent interest: it states a novel bound on the approximation error with respect to the optimal average reward of that of a policy optimal for the discounted reward. Since learning with discounted rewards is generally easier, this discussion further justifies finding a fair policy for the average reward by learning a fair policy for the discounted reward. Thus, we describe how several classic deep RL algorithms can be adapted to our fair optimization problem, and we validate our approach with extensive experiments in three different domains.

cs.AI↗

arXiv2020

Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning

Deep Reinforcement Learning (RL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. To alleviate this issue, we propose to exploit the symmetries present in robotic tasks. Intuitively, symmetries from observed trajectories define transformations that leave the space of feasible RL trajectories invariant and can be used to generate new feasible trajectories, which could be used for training. Based on this data augmentation idea, we formulate a general framework, called Invariant Transform Experience Replay that we present with two techniques: (i) Kaleidoscope Experience Replay exploits reflectional symmetries and (ii) Goal-augmented Experience Replay which takes advantage of lax goal definitions. In the Fetch tasks from OpenAI Gym, our experimental results show significant increases in learning rates and success rates. Particularly, we attain a 13, 3, and 5 times speedup in the pushing, sliding, and pick-and-place tasks respectively in the multi-goal setting. Performance gains are also observed in similar tasks with obstacles and we successfully deployed a trained policy on a real Baxter robot. Our work demonstrates that invariant transformations on RL trajectories are a promising methodology to speed up learning in deep RL.

cs.RO↗

arXiv2020

Reinforcement Learning

Reinforcement learning (RL) is a general framework for adaptive control, which has proven to be efficient in many domains, e.g., board games, video games or autonomous vehicles. In such problems, an agent faces a sequential decision-making problem where, at every time step, it observes its state, performs an action, receives a reward and moves to a new state. An RL agent learns by trial and error a good policy (or controller) based on observations and numeric reward feedback on the previously performed action. In this chapter, we present the basic framework of RL and recall the two main families of approaches that have been developed to learn a good policy. The first one, which is value-based, consists in estimating the value of an optimal policy, value from which a policy can be recovered, while the other, called policy search, directly works in a policy space. Actor-critic methods can be seen as a policy search technique where the policy value that is learned guides the policy improvement. Besides, we give an overview of some extensions of the standard RL framework, notably when risk-averse behavior needs to be taken into account or when rewards are not available or not known.

cs.LG↗

arXiv2019

Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation

Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in order to reuse more efficiently observed data. The first one called Kaleidoscope Experience Replay exploits reflectional symmetries, while the second called Goal-augmented Experience Replay takes advantage of lax goal definitions. Our preliminary experimental results show a large increase in learning speed.

cs.AI↗

arXiv2019

Fairness in Reinforcement Learning

Decision support systems (e.g., for ecological conservation) and autonomous systems (e.g., adaptive controllers in smart cities) start to be deployed in real applications. Although their operations often impact many users or stakeholders, no fairness consideration is generally taken into account in their design, which could lead to completely unfair outcomes for some users or stakeholders. To tackle this issue, we advocate for the use of social welfare functions that encode fairness and present this general novel problem in the context of (deep) reinforcement learning, although it could possibly be extended to other machine learning tasks.

cs.LG↗

arXiv2019

Exploiting the Sign of the Advantage Function to Learn Deterministic Policies in Continuous Domains

In the context of learning deterministic policies in continuous domains, we revisit an approach, which was first proposed in Continuous Actor Critic Learning Automaton (CACLA) and later extended in Neural Fitted Actor Critic (NFAC). This approach is based on a policy update different from that of deterministic policy gradient (DPG). Previous work has observed its excellent performance empirically, but a theoretical justification is lacking. To fill this gap, we provide a theoretical explanation to motivate this unorthodox policy update by relating it to another update and making explicit the objective function of the latter. We furthermore discuss in depth the properties of these updates to get a deeper understanding of the overall approach. In addition, we extend it and propose a new trust region algorithm, Penalized NFAC (PeNFAC). Finally, we experimentally demonstrate in several classic control problems that it surpasses the state-of-the-art algorithms to learn deterministic policies.

cs.LG↗

arXiv2019

Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods. However, most existing models assume that social effects from friend users are static and under the forms of constant weights or fixed constraints. To relax this strong assumption, in this paper, we propose dual graph attention networks to collaboratively learn representations for two-fold social effects, where one is modeled by a user-specific attention weight and the other is modeled by a dynamic and context-aware attention weight. We also extend the social effects in user domain to item domain, so that information from related items can be leveraged to further alleviate the data sparsity problem. Furthermore, considering that different social effects in two domains could interact with each other and jointly influence user preferences for items, we propose a new policy-based fusion strategy based on contextual multi-armed bandit to weigh interactions of various social effects. Experiments on one benchmark dataset and a commercial dataset verify the efficacy of the key components in our model. The results show that our model achieves great improvement for recommendation accuracy compared with other state-of-the-art social recommendation methods.

cs.IR↗

arXiv2018

Optimal Threshold Policies for Robust Data Center Control

With the simultaneous rise of energy costs and demand for cloud computing, efficient control of data centers becomes crucial. In the data center control problem, one needs to plan at every time step how many servers to switch on or off in order to meet stochastic job arrivals while trying to minimize electricity consumption. This problem becomes particularly challenging when servers can be of various types and jobs from different classes can only be served by certain types of server, as it is often the case in real data centers. We model this problem as a robust Markov Decision Process (i.e., the transition function is not assumed to be known precisely). We give sufficient conditions (which seem to be reasonable and satisfied in practice) guaranteeing that an optimal threshold policy exists. This property can then be exploited in the design of an efficient solving method, which we provide. Finally, we present some experimental results demonstrating the practicability of our approach and compare with a previous related approach based on model predictive control.

cs.PF↗

arXiv2018

An Efficient Primal-Dual Algorithm for Fair Combinatorial Optimization Problems

We consider a general class of combinatorial optimization problems including among others allocation, multiple knapsack, matching or travelling salesman problems. The standard version of those problems is the maximum weight optimization problem where a sum of values is optimized. However, the sum is not a good aggregation function when the fairness of the distribution of those values (corresponding for example to different agents' utilities or criteria) is important. In this paper, using the generalized Gini index (GGI), a well-known inequality measure, instead of the sum to model fairness, we formulate a new general problem, that we call fair combinatorial optimization. Although GGI is a non-linear aggregating function, a $0,1$-linear program (IP) can be formulated for finding a GGI-optimal solution by exploiting a linearization of GGI proposed by Ogryczak and Sliwinski. However, the time spent by commercial solvers (e.g., CPLEX, Gurobi...) for solving (IP) increases very quickly with instances' size and can reach hours even for relatively small-sized ones. As a faster alternative, we propose a heuristic for solving (IP) based on a primal-dual approach using Lagrangian decomposition. %We experimentally evaluate our methods against the exact solution of (IP) by CPLEX on several fair optimization problems related to matching to demonstrate the efficiency of our proposition. We demonstrate the efficiency of our method by evaluating it against the exact solution of (IP) by CPLEX on several fair optimization problems related to matching. The numerical results show that our method outputs in a very short time efficient solutions giving lower bounds that CPLEX may take several orders of magnitude longer to obtain. Moreover, for instances for which we know the optimal value, these solutions are quasi-optimal with optimality gap less than 0.3%.

cs.DS↗