arXiv subjects

Harshad Khadilkar

Publications and source records attributed to Harshad Khadilkar.

36 records · Page 2Linked to original sources

arXiv2023

Supplementing Gradient-Based Reinforcement Learning with Simple Evolutionary Ideas

We present a simple, sample-efficient algorithm for introducing large but directed learning steps in reinforcement learning (RL), through the use of evolutionary operators. The methodology uses a population of RL agents training with a common experience buffer, with occasional crossovers and mutations of the agents in order to search efficiently through the policy space. Unlike prior literature on combining evolutionary search (ES) with RL, this work does not generate a distribution of agents from a common mean and covariance matrix. Neither does it require the evaluation of the entire population of policies at every time step. Instead, we focus on gradient-based training throughout the life of every policy (individual), with a sparse amount of evolutionary exploration. The resulting algorithm is shown to be robust to hyperparameter variations. As a surprising corollary, we show that simply initialising and training multiple RL agents with a common memory (with no further evolutionary updates) outperforms several standard RL baselines.

cs.NE↗

arXiv2023

Follow your Nose: Using General Value Functions for Directed Exploration in Reinforcement Learning

Improving sample efficiency is a key challenge in reinforcement learning, especially in environments with large state spaces and sparse rewards. In literature, this is resolved either through the use of auxiliary tasks (subgoals) or through clever exploration strategies. Exploration methods have been used to sample better trajectories in large environments while auxiliary tasks have been incorporated where the reward is sparse. However, few studies have attempted to tackle both large scale and reward sparsity at the same time. This paper explores the idea of combining exploration with auxiliary task learning using General Value Functions (GVFs) and a directed exploration strategy. We present a way to learn value functions which can be used to sample actions and provide directed exploration. Experiments on navigation tasks with varying grid sizes demonstrate the performance advantages over several competitive baselines.

cs.LG↗

arXiv2022

Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning

A significant challenge in reinforcement learning is quantifying the complex relationship between actions and long-term rewards. The effects may manifest themselves over a long sequence of state-action pairs, making them hard to pinpoint. In this paper, we propose a method to link transitions with significant deviations in state with unusually large variations in subsequent rewards. Such transitions are marked as possible causal effects, and the corresponding state-action pairs are added to a separate replay buffer. In addition, we include \textit{contrastive} samples corresponding to transitions from a similar state but with differing actions. Including this Contrastive Experience Replay (CER) during training is shown to outperform standard value-based methods on 2D navigation tasks. We believe that CER can be useful for a broad class of learning tasks, including for any off-policy reinforcement learning algorithm.

cs.LG↗

arXiv2022

A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions

Modern deep neural network models are known to erroneously classify out-of-distribution (OOD) test data into one of the in-distribution (ID) training classes with high confidence. This can have disastrous consequences for safety-critical applications. A popular mitigation strategy is to train a separate classifier that can detect such OOD samples at the test time. In most practical settings OOD examples are not known at the train time, and hence a key question is: how to augment the ID data with synthetic OOD samples for training such an OOD detector? In this paper, we propose a novel Compounded Corruption technique for the OOD data augmentation termed CnC. One of the major advantages of CnC is that it does not require any hold-out data apart from the training set. Further, unlike current state-of-the-art (SOTA) techniques, CnC does not require backpropagation or ensembling at the test time, making our method much faster at inference. Our extensive comparison with 20 methods from the major conferences in last 4 years show that a model trained using CnC based data augmentation, significantly outperforms SOTA, both in terms of OOD detection accuracy as well as inference time. We include a detailed post-hoc analysis to investigate the reasons for the success of our method and identify higher relative entropy and diversity of CnC samples as probable causes. We also provide theoretical insights via a piece-wise decomposition analysis on a two-dimensional dataset to reveal (visually and quantitatively) that our approach leads to a tighter boundary around ID classes, leading to better detection of OOD samples. Source code link: https://github.com/cnc-ood

cs.CV↗

arXiv2022

Solving the capacitated vehicle routing problem with timing windows using rollouts and MAX-SAT

The vehicle routing problem is a well known class of NP-hard combinatorial optimisation problems in literature. Traditional solution methods involve either carefully designed heuristics, or time-consuming metaheuristics. Recent work in reinforcement learning has been a promising alternative approach, but has found it difficult to compete with traditional methods in terms of solution quality. This paper proposes a hybrid approach that combines reinforcement learning, policy rollouts, and a satisfiability solver to enable a tunable tradeoff between computation times and solution quality. Results on a popular public data set show that the algorithm is able to produce solutions closer to optimal levels than existing learning based approaches, and with shorter computation times than meta-heuristics. The approach requires minimal design effort and is able to solve unseen problems of arbitrary scale without additional training. Furthermore, the methodology is generalisable to other combinatorial optimisation problems.

cs.AI↗

arXiv2022

A Learning Based Framework for Handling Uncertain Lead Times in Multi-Product Inventory Management

Most existing literature on supply chain and inventory management consider stochastic demand processes with zero or constant lead times. While it is true that in certain niche scenarios, uncertainty in lead times can be ignored, most real-world scenarios exhibit stochasticity in lead times. These random fluctuations can be caused due to uncertainty in arrival of raw materials at the manufacturer's end, delay in transportation, an unforeseen surge in demands, and switching to a different vendor, to name a few. Stochasticity in lead times is known to severely degrade the performance in an inventory management system, and it is only fair to abridge this gap in supply chain system through a principled approach. Motivated by the recently introduced delay-resolved deep Q-learning (DRDQN) algorithm, this paper develops a reinforcement learning based paradigm for handling uncertainty in lead times (\emph{action delay}). Through empirical evaluations, it is further shown that the inventory management with uncertain lead times is not only equivalent to that of delay in information sharing across multiple echelons (\emph{observation delay}), a model trained to handle one kind of delay is capable to handle delays of another kind without requiring to be retrained. Finally, we apply the delay-resolved framework to scenarios comprising of multiple products subjected to stochasticity in lead times, and elucidate how the delay-resolved framework negates the effect of any delay to achieve near-optimal performance.

cs.LG↗

arXiv2021

Learning to Minimize Cost-to-Serve for Multi-Node Multi-Product Order Fulfilment in Electronic Commerce

We describe a novel decision-making problem developed in response to the demands of retail electronic commerce (e-commerce). While working with logistics and retail industry business collaborators, we found that the cost of delivery of products from the most opportune node in the supply chain (a quantity called the cost-to-serve or CTS) is a key challenge. The large scale, high stochasticity, and large geographical spread of e-commerce supply chains make this setting ideal for a carefully designed data-driven decision-making algorithm. In this preliminary work, we focus on the specific subproblem of delivering multiple products in arbitrary quantities from any warehouse to multiple customers in each time period. We compare the relative performance and computational efficiency of several baselines, including heuristics and mixed-integer linear programming. We show that a reinforcement learning based algorithm is competitive with these policies, with the potential of efficient scale-up in the real world.

cs.AI↗

arXiv2021

A simulation driven optimization algorithm for scheduling sorting center operations

Parcel sorting operations in logistics enterprises aim to achieve a high throughput of parcels through sorting centers. These sorting centers are composed of large circular conveyor belts on which incoming parcels are placed, with multiple arms known as chutes for sorting the parcels by destination, followed by packing into roller cages and loading onto outbound trucks. Modern sorting systems need to complement their hardware innovations with sophisticated algorithms and software to map destinations and workforce to specific chutes. While state of the art systems operate with fixed mappings, we propose an optimization approach that runs before every shift, and uses real-time forecast of destination demand and labor availability in order to maximize throughput. We use simulation to improve the performance and robustness of the optimization solution to stochasticity in the environment, through closed-loop tuning of the optimization parameters.

eess.SY↗

arXiv2021

Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays

Several real-world scenarios, such as remote control and sensing, are comprised of action and observation delays. The presence of delays degrades the performance of reinforcement learning (RL) algorithms, often to such an extent that algorithms fail to learn anything substantial. This paper formally describes the notion of Markov Decision Processes (MDPs) with stochastic delays and shows that delayed MDPs can be transformed into equivalent standard MDPs (without delays) with significantly simplified cost structure. We employ this equivalence to derive a model-free Delay-Resolved RL framework and show that even a simple RL algorithm built upon this framework achieves near-optimal rewards in environments with stochastic delays in actions and observations. The delay-resolved deep Q-network (DRDQN) algorithm is bench-marked on a variety of environments comprising of multi-step and stochastic delays and results in better performance, both in terms of achieving near-optimal rewards and minimizing the computational overhead thereof, with respect to the currently established algorithms.

cs.LG↗

arXiv2021

Fast Approximate Solutions using Reinforcement Learning for Dynamic Capacitated Vehicle Routing with Time Windows

This paper develops an inherently parallelised, fast, approximate learning-based solution to the generic class of Capacitated Vehicle Routing Problems 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 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.

cs.AI↗

arXiv2021

School of hard knocks: Curriculum analysis for Pommerman with a fixed computational budget

Pommerman is a hybrid cooperative/adversarial multi-agent environment, with challenging characteristics in terms of partial observability, limited or no communication, sparse and delayed rewards, and restrictive computational time limits. This makes it a challenging environment for reinforcement learning (RL) approaches. In this paper, we focus on developing a curriculum for learning a robust and promising policy in a constrained computational budget of 100,000 games, starting from a fixed base policy (which is itself trained to imitate a noisy expert policy). All RL algorithms starting from the base policy use vanilla proximal-policy optimization (PPO) with the same reward function, and the only difference between their training is the mix and sequence of opponent policies. One expects that beginning training with simpler opponents and then gradually increasing the opponent difficulty will facilitate faster learning, leading to more robust policies compared against a baseline where all available opponent policies are introduced from the start. We test this hypothesis and show that within constrained computational budgets, it is in fact better to "learn in the school of hard knocks", i.e., against all available opponent policies nearly from the start. We also include ablation studies where we study the effect of modifying the base environment properties of ammo and bomb blast strength on the agent performance.

cs.AI↗

arXiv2020

SIBRE: Self Improvement Based REwards for Adaptive Feedback in Reinforcement Learning

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL algorithm, and consists of rewarding improvement over the agent's own past performance. We prove that SIBRE converges in expectation under the same conditions as the original RL algorithm. The reshaped rewards help discriminate between policies when the original rewards are weakly discriminated or sparse. Experiments on several well-known benchmark environments with different RL algorithms show that SIBRE converges to the optimal policy faster and more stably. We also perform sensitivity analysis with respect to hyper-parameters, in comparison with baseline RL algorithms.

cs.LG↗

arXiv2020

Sample Efficient Training in Multi-Agent Adversarial Games with Limited Teammate Communication

We describe our solution approach for Pommerman TeamRadio, a competition environment associated with NeurIPS 2019. The defining feature of our algorithm is achieving sample efficiency within a restrictive computational budget while beating the previous years learning agents. The proposed algorithm (i) uses imitation learning to seed the policy, (ii) explicitly defines the communication protocol between the two teammates, (iii) shapes the reward to provide a richer feedback signal to each agent during training and (iv) uses masking for catastrophic bad actions. We describe extensive tests against baselines, including those from the 2019 competition leaderboard, and also a specific investigation of the learned policy and the effect of each modification on performance. We show that the proposed approach is able to achieve competitive performance within half a million games of training, significantly faster than other studies in the literature.

cs.LG↗

arXiv2020

A Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing

We propose a Deep Reinforcement Learning (Deep RL) algorithm for solving the online 3D bin packing problem for an arbitrary number of bins and any bin size. The focus is on producing decisions that can be physically implemented by a robotic loading arm, a laboratory prototype used for testing the concept. The problem considered in this paper is novel in two ways. First, unlike the traditional 3D bin packing problem, we assume that the entire set of objects to be packed is not known a priori. Instead, a fixed number of upcoming objects is visible to the loading system, and they must be loaded in the order of arrival. Second, the goal is not to move objects from one point to another via a feasible path, but to find a location and orientation for each object that maximises the overall packing efficiency of the bin(s). Finally, the learnt model is designed to work with problem instances of arbitrary size without retraining. Simulation results show that the RL-based method outperforms state-of-the-art online bin packing heuristics in terms of empirical competitive ratio and volume efficiency.

cs.AI↗

arXiv2020

Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains

This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains. The problem description and solution are both adapted from a real-world business solution. The novelty of this problem with respect to supply chain literature is (i) we consider concurrent inventory management of a large number (50 to 1000) of products with shared capacity, (ii) we consider a multi-node supply chain consisting of a warehouse which supplies three stores, (iii) the warehouse, stores, and transportation from warehouse to stores have finite capacities, (iv) warehouse and store replenishment happen at different time scales and with realistic time lags, and (v) demand for products at the stores is stochastic. We describe a novel formulation in a multi-agent (hierarchical) reinforcement learning framework that can be used for parallelised decision-making, and use the advantage actor critic (A2C) algorithm with quantised action spaces to solve the problem. Experiments show that the proposed approach is able to handle a multi-objective reward comprised of maximising product sales and minimising wastage of perishable products.

cs.LG↗

arXiv2020

Optimising Lockdown Policies for Epidemic Control using Reinforcement Learning

In the context of the ongoing Covid-19 pandemic, several reports and studies have attempted to model and predict the spread of the disease. There is also intense debate about policies for limiting the damage, both to health and to the economy. On the one hand, the health and safety of the population is the principal consideration for most countries. On the other hand, we cannot ignore the potential for long-term economic damage caused by strict nation-wide lockdowns. In this working paper, we present a quantitative way to compute lockdown decisions for individual cities or regions, while balancing health and economic considerations. Furthermore, these policies are learnt automatically by the proposed algorithm, as a function of disease parameters (infectiousness, gestation period, duration of symptoms, probability of death) and population characteristics (density, movement propensity). We account for realistic considerations such as imperfect lockdowns, and show that the policy obtained using reinforcement learning is a viable quantitative approach towards lockdowns.

physics.soc-ph↗

arXiv2019

Accelerating Training in Pommerman with Imitation and Reinforcement Learning

The Pommerman simulation was recently developed to mimic the classic Japanese game Bomberman, and focuses on competitive gameplay in a multi-agent setting. We focus on the 2$\times$2 team version of Pommerman, developed for a competition at NeurIPS 2018. Our methodology involves training an agent initially through imitation learning on a noisy expert policy, followed by a proximal-policy optimization (PPO) reinforcement learning algorithm. The basic PPO approach is modified for stable transition from the imitation learning phase through reward shaping, action filters based on heuristics, and curriculum learning. The proposed methodology is able to beat heuristic and pure reinforcement learning baselines with a combined 100,000 training games, significantly faster than other non-tree-search methods in literature. We present results against multiple agents provided by the developers of the simulation, including some that we have enhanced. We include a sensitivity analysis over different parameters, and highlight undesirable effects of some strategies that initially appear promising. Since Pommerman is a complex multi-agent competitive environment, the strategies developed here provide insights into several real-world problems with characteristics such as partial observability, decentralized execution (without communication), and very sparse and delayed rewards.

cs.LG↗

arXiv2019

Reinforcement Learning for Multi-Objective Optimization of Online Decisions in High-Dimensional Systems

This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while the micro-level behaviour of the system can be broadly captured by analytical expressions or simulation, the macro-level or emergent behaviour is complicated by non-linearity, constraints, and stochasticity. If we represent the set of concurrent decisions to be computed as a vector, each element of the vector is assumed to be a continuous variable, and the number of such elements is arbitrarily large and variable from one problem instance to another. We first formulate the decision-making problem as a canonical reinforcement learning (RL) problem, which can be solved using purely data-driven techniques. We modify a standard approach known as advantage actor critic (A2C) to ensure its suitability to the problem at hand, and compare its performance to that of baseline approaches on the specific instance of a multi-product inventory management task. The key modifications include a parallelised formulation of the decision-making task, and a training procedure that explicitly recognises the quantitative relationship between different decisions. We also present experimental results probing the learned policies, and their robustness to variations in the data.

cs.AI↗