Search Results for author:
Found 26 papers, 7 papers with code
Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization
While this strategy has proven effective, the training methodology requires a lot of human preference annotation (usually in the order of tens of thousands) to train $\varphi$.
Transformers are Expressive, But Are They Expressive Enough for Regression?
Expressivity of a neural network is the class of functions it can approximate.
Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning
Query-focused Summarization (QfS) deals with systems that generate summaries from document(s) based on a query.
Multi-Agent Learning of Efficient Fulfilment and Routing Strategies in E-Commerce
This paper presents an integrated algorithmic framework for minimising product delivery costs in e-commerce (known as the cost-to-serve or C2S).
Using General Value Functions to Learn Domain-Backed Inventory Management Policies
We consider the inventory management problem, where the goal is to balance conflicting objectives such as availability and wastage of a large range of products in a store.
Using Linear Regression for Iteratively Training Neural Networks
The key idea is the observation that the input to every neuron in a neural network is a linear combination of the activations of neurons in the previous layer, as well as the parameters (weights and biases) of the layer.
DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces
The ability to learn robust policies while generalizing over large discrete action spaces is an open challenge for intelligent systems, especially in noisy environments that face the curse of dimensionality.
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.
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.
A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions
One of the major advantages of CnC is that it does not require any hold-out data apart from the training set.
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.
Follow your Nose: Using General Value Functions for Directed Exploration in Reinforcement Learning
Exploration methods have been used to sample better trajectories in large environments while auxiliary tasks have been incorporated where the reward is sparse.
A Learning Based Framework for Handling Uncertain Lead Times in Multi-Product Inventory Management
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.
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).
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.
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.
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).
School of hard knocks: Curriculum analysis for Pommerman with a fixed computational budget
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).
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.
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.
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.
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.
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.
Accelerating Training in Pommerman with Imitation and Reinforcement Learning
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.
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.
Learning representations for sentiment classification using Multi-task framework
Most of the existing state of the art sentiment classification techniques involve the use of pre-trained embeddings.
