Search Results for author:
Found 38 papers, 6 papers with code
Clustering Markov Decision Processes For Continual Transfer
The source subset forms an `$\epsilon$-net' over the original set of MDPs, in the sense that for each previous MDP $M_p$, there is a source $M^s$ whose optimal policy has $<\epsilon$ regret in $M_p$.
Bayesian Policy Reuse
We formalise the problem of policy reuse, and present an algorithm for efficiently responding to a novel task instance by reusing a policy from the library of existing policies, where the choice is based on observed 'signals' which correlate to policy performance.
Hierarchy through Composition with Linearly Solvable Markov Decision Processes
Hierarchical architectures are critical to the scalability of reinforcement learning methods.
Hierarchy Through Composition with Multitask LMDPs
Hierarchical architectures are critical to the scalability of reinforcement learning methods.
Hierarchical Subtask Discovery With Non-Negative Matrix Factorization
Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains.
Reasoning about Unforeseen Possibilities During Policy Learning
Methods for learning optimal policies in autonomous agents often assume that the way the domain is conceptualised---its possible states and actions and their causal structure---is known in advance and does not change during learning.
Symbol Emergence in Cognitive Developmental Systems: a Survey
However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered.
Will it Blend? Composing Value Functions in Reinforcement Learning
An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks.
Incremental Hierarchical Reinforcement Learning with Multitask LMDPs
Exploration is a well known challenge in Reinforcement Learning.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning
Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds with respect to sample complexity.
Transfer Learning for Prosthetics Using Imitation Learning
In this paper, We Apply Reinforcement learning (RL) techniques to train a realistic biomechanical model to work with different people and on different walking environments.
Learning Portable Representations for High-Level Planning
We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments.
Estimation of Body Mass Index from Photographs using Deep Convolutional Neural Networks
Obesity is an important concern in public health, and Body Mass Index is one of the useful (and proliferant) measures.
Using Objective Bayesian Methods to Determine the Optimal Degree of Curvature within the Loss Landscape
The efficacy of the width of the basin of attraction surrounding a minimum in parameter space as an indicator for the generalizability of a model parametrization is a point of contention surrounding the training of artificial neural networks, with the dominant view being that wider areas in the landscape reflect better generalizability by the trained model.
If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
Our results therefore suggest that, in the shallow-to-moderate depth setting, critical initialisation provides zero performance gains when compared to off-critical initialisations and that searching for off-critical initialisations that might improve training speed or generalisation, is likely to be a fruitless endeavour.
A Boolean Task Algebra for Reinforcement Learning
The ability to compose learned skills to solve new tasks is an important property of lifelong-learning agents.
Online Constrained Model-based Reinforcement Learning
The environment's dynamics are learned from limited training data and can be reused in new task instances without retraining.
Logical Composition in Lifelong Reinforcement Learning
The ability to produce novel behaviours from existing skills is an important property of lifelong learning agents.
Autonomous Learning of Object-Centric Abstractions for High-Level Planning
Such representations can immediately be transferred between tasks that share the same types of objects, resulting in agents that require fewer samples to learn a model of a new task.
Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization
Based upon these findings, we show that gradient flow in sparse networks can be improved by reconsidering aspects of the architecture design and the training regime.
The Role of Learning Regime, Architecture and Dataset Structure on Systematic Generalization in Simple Neural Networks
We introduce a minimal space of datasets with systematic and non-systematic features in both the input and output.
Generalisation in Lifelong Reinforcement Learning through Logical Composition
We leverage logical composition in reinforcement learning to create a framework that enables an agent to autonomously determine whether a new task can be immediately solved using its existing abilities, or whether a task-specific skill should be learned.
Learning to Follow Language Instructions with Compositional Policies
We propose a framework that learns to execute natural language instructions in an environment consisting of goal-reaching tasks that share components of their task descriptions.
Learning Abstract and Transferable Representations for Planning
We propose a framework for autonomously learning state abstractions of an agent's environment, given a set of skills.
World Value Functions: Knowledge Representation for Multitask Reinforcement Learning
In this work we propose world value functions (WVFs), which are a type of general value function with mastery of the world - they represent not only how to solve a given task, but also how to solve any other goal-reaching task.
Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
The agent can then flexibly compose them both logically and temporally to provably achieve temporal logic specifications in any regular language, such as regular fragments of linear temporal logic.
World Value Functions: Knowledge Representation for Learning and Planning
We propose world value functions (WVFs), a type of goal-oriented general value function that represents how to solve not just a given task, but any other goal-reaching task in an agent's environment.
A Framework for Undergraduate Data Collection Strategies for Student Support Recommendation Systems in Higher Education
While much effort and detail has gone into the expansion of explaining algorithmic decision making in this context, there is still a need to develop data collection strategies Therefore, the purpose of this paper is to outline a data collection framework specific to recommender systems within this context in order to reduce collection biases, understand student characteristics, and find an ideal way to infer optimal influences on the student journey.
Comparing Synthetic Tabular Data Generation Between a Probabilistic Model and a Deep Learning Model for Education Use Cases
The ability to generate synthetic data has a variety of use cases across different domains.
Reinforcement Learning in Education: A Multi-Armed Bandit Approach
Advances in reinforcement learning research have demonstrated the ways in which different agent-based models can learn how to optimally perform a task within a given environment.
Hierarchically Composing Level Generators for the Creation of Complex Structures
Procedural content generation (PCG) is a growing field, with numerous applications in the video game industry and great potential to help create better games at a fraction of the cost of manual creation.
The challenge of redundancy on multi-agent value factorisation
In the field of cooperative multi-agent reinforcement learning (MARL), the standard paradigm is the use of centralised training and decentralised execution where a central critic conditions the policies of the cooperative agents based on a central state.
ROSARL: Reward-Only Safe Reinforcement Learning
A common solution is for a human expert to define either a penalty in the reward function or a cost to be minimised when reaching unsafe states.
Planning to Learn: A Novel Algorithm for Active Learning during Model-Based Planning
First, we compare performance of SI to Bayesian reinforcement learning (RL) schemes designed to solve similar problems.
Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies
To this end, we introduce a neural network architecture, the Decision Adapter, which generates the weights of an adapter module and conditions the behaviour of an agent on the context information.
Generalisable Agents for Neural Network Optimisation
Optimising deep neural networks is a challenging task due to complex training dynamics, high computational requirements, and long training times.
Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure
We present counting reward automata-a finite state machine variant capable of modelling any reward function expressible as a formal language.
Towards Financially Inclusive Credit Products Through Financial Time Series Clustering
Financial inclusion ensures that individuals have access to financial products and services that meet their needs.
