arXiv subjects

Steven James

Publications and source records attributed to Steven James.

36 records · Page 2Linked to original sources

arXiv2023

ROSARL: Reward-Only Safe Reinforcement Learning

An important problem in reinforcement learning is designing agents that learn to solve tasks safely in an environment. 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. However, this is non-trivial, since too small a penalty may lead to agents that reach unsafe states, while too large a penalty increases the time to convergence. Additionally, the difficulty in designing reward or cost functions can increase with the complexity of the problem. Hence, for a given environment with a given set of unsafe states, we are interested in finding the upper bound of rewards at unsafe states whose optimal policies minimise the probability of reaching those unsafe states, irrespective of task rewards. We refer to this exact upper bound as the "Minmax penalty", and show that it can be obtained by taking into account both the controllability and diameter of an environment. We provide a simple practical model-free algorithm for an agent to learn this Minmax penalty while learning the task policy, and demonstrate that using it leads to agents that learn safe policies in high-dimensional continuous control environments.

cs.LG↗

arXiv2022

Combining Evolutionary Search with Behaviour Cloning for Procedurally Generated Content

In this work, we consider the problem of procedural content generation for video game levels. Prior approaches have relied on evolutionary search (ES) methods capable of generating diverse levels, but this generation procedure is slow, which is problematic in real-time settings. Reinforcement learning (RL) has also been proposed to tackle the same problem, and while level generation is fast, training time can be prohibitively expensive. We propose a framework to tackle the procedural content generation problem that combines the best of ES and RL. In particular, our approach first uses ES to generate a sequence of levels evolved over time, and then uses behaviour cloning to distil these levels into a policy, which can then be queried to produce new levels quickly. We apply our approach to a maze game and Super Mario Bros, with our results indicating that our approach does in fact decrease the time required for level generation, especially when an increasing number of valid levels are required.

cs.AI↗

arXiv2022

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. This is achieved by equipping an agent with an internal goal space defined as all the world states where it experiences a terminal transition. The agent can then modify the standard task rewards to define its own reward function, which provably drives it to learn how to achieve all reachable internal goals, and the value of doing so in the current task. We demonstrate two key benefits of WVFs in the context of learning and planning. In particular, given a learned WVF, an agent can compute the optimal policy in a new task by simply estimating the task's reward function. Furthermore, we show that WVFs also implicitly encode the transition dynamics of the environment, and so can be used to perform planning. Experimental results show that WVFs can be learned faster than regular value functions, while their ability to infer the environment's dynamics can be used to integrate learning and planning methods to further improve sample efficiency.

cs.AI↗

arXiv2022

World Value Functions: Knowledge Representation for Multitask Reinforcement Learning

An open problem in artificial intelligence is how to learn and represent knowledge that is sufficient for a general agent that needs to solve multiple tasks in a given world. 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. To achieve this, we equip the agent with an internal goal space defined as all the world states where it experiences a terminal transition - a task outcome. The agent can then modify task rewards to define its own reward function, which provably drives it to learn how to achieve all achievable internal goals, and the value of doing so in the current task. We demonstrate a number of benefits of WVFs. When the agent's internal goal space is the entire state space, we demonstrate that the transition function can be inferred from the learned WVF, which allows the agent to plan using learned value functions. Additionally, we show that for tasks in the same world, a pretrained agent that has learned any WVF can then infer the policy and value function for any new task directly from its rewards. Finally, an important property for long-lived agents is the ability to reuse existing knowledge to solve new tasks. Using WVFs as the knowledge representation for learned tasks, we show that an agent is able to solve their logical combination zero-shot, resulting in a combinatorially increasing number of skills throughout their lifetime.

cs.LG↗

arXiv2022

Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning

In this work, we investigate the properties of data that cause popular representation learning approaches to fail. In particular, we find that in environments where states do not significantly overlap, variational autoencoders (VAEs) fail to learn useful features. We demonstrate this failure in a simple gridworld domain, and then provide a solution in the form of metric learning. However, metric learning requires supervision in the form of a distance function, which is absent in reinforcement learning. To overcome this, we leverage the sequential nature of states in a replay buffer to approximate a distance metric and provide a weak supervision signal, under the assumption that temporally close states are also semantically similar. We modify a VAE with triplet loss and demonstrate that this approach is able to learn useful features for downstream tasks, without additional supervision, in environments where standard VAEs fail.

cs.LG↗

arXiv2022

Learning Abstract and Transferable Representations for Planning

We are concerned with the question of how an agent can acquire its own representations from sensory data. We restrict our focus to learning representations for long-term planning, a class of problems that state-of-the-art learning methods are unable to solve. We propose a framework for autonomously learning state abstractions of an agent's environment, given a set of skills. Importantly, these abstractions are task-independent, and so can be reused to solve new tasks. We demonstrate how an agent can use an existing set of options to acquire representations from ego- and object-centric observations. These abstractions can immediately be reused by the same agent in new environments. We show how to combine these portable representations with problem-specific ones to generate a sound description of a specific task that can be used for abstract planning. Finally, we show how to autonomously construct a multi-level hierarchy consisting of increasingly abstract representations. Since these hierarchies are transferable, higher-order concepts can be reused in new tasks, relieving the agent from relearning them and improving sample efficiency. Our results demonstrate that our approach allows an agent to transfer previous knowledge to new tasks, improving sample efficiency as the number of tasks increases.

cs.LG↗

arXiv2022

Adaptive Online Value Function Approximation with Wavelets

Using function approximation to represent a value function is necessary for continuous and high-dimensional state spaces. Linear function approximation has desirable theoretical guarantees and often requires less compute and samples than neural networks, but most approaches suffer from an exponential growth in the number of functions as the dimensionality of the state space increases. In this work, we introduce the wavelet basis for reinforcement learning. Wavelets can effectively be used as a fixed basis and additionally provide the ability to adaptively refine the basis set as learning progresses, making it feasible to start with a minimal basis set. This adaptive method can either increase the granularity of the approximation at a point in state space, or add in interactions between different dimensions as necessary. We prove that wavelets are both necessary and sufficient if we wish to construct a function approximator that can be adaptively refined without loss of precision. We further demonstrate that a fixed wavelet basis set performs comparably against the high-performing Fourier basis on Mountain Car and Acrobot, and that the adaptive methods provide a convenient approach to addressing an oversized initial basis set, while demonstrating performance comparable to, or greater than, the fixed wavelet basis.

cs.LG↗

arXiv2022

Automatic Encoding and Repair of Reactive High-Level Tasks with Learned Abstract Representations

We present a framework that, given a set of skills a robot can perform, abstracts sensor data into symbols that we use to automatically encode the robot's capabilities in Linear Temporal Logic. We specify reactive high-level tasks based on these capabilities, for which a strategy is automatically synthesized and executed on the robot, if the task is feasible. If a task is not feasible given the robot's capabilities, we present two methods, one enumeration-based and one synthesis-based, for automatically suggesting additional skills for the robot or modifications to existing skills that would make the task feasible. We demonstrate our framework on a Baxter robot manipulating blocks on a table, a Baxter robot manipulating plates on a table, and a Kinova arm manipulating vials, with multiple sensor modalities, including raw images.

cs.RO↗

arXiv2022

Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels

Procedurally generated video game content has the potential to drastically reduce the content creation budget of game developers and large studios. However, adoption is hindered by limitations such as slow generation, as well as low quality and diversity of content. We introduce an evolutionary search-based approach for evolving level generators using novelty search to procedurally generate diverse levels in real time, without requiring training data or detailed domain-specific knowledge. We test our method on two domains, and our results show an order of magnitude speedup in generation time compared to existing methods while obtaining comparable metric scores. We further demonstrate the ability to generalise to arbitrary-sized levels without retraining.

cs.NE↗

arXiv2022

Towards Objective Metrics for Procedurally Generated Video Game Levels

With increasing interest in procedural content generation by academia and game developers alike, it is vital that different approaches can be compared fairly. However, evaluating procedurally generated video game levels is often difficult, due to the lack of standardised, game-independent metrics. In this paper, we introduce two simulation-based evaluation metrics that involve analysing the behaviour of an A* agent to measure the diversity and difficulty of generated levels in a general, game-independent manner. Diversity is calculated by comparing action trajectories from different levels using the edit distance, and difficulty is measured as how much exploration and expansion of the A* search tree is necessary before the agent can solve the level. We demonstrate that our diversity metric is more robust to changes in level size and representation than current methods and additionally measures factors that directly affect playability, instead of focusing on visual information. The difficulty metric shows promise, as it correlates with existing estimates of difficulty in one of the tested domains, but it does face some challenges in the other domain. Finally, to promote reproducibility, we publicly release our evaluation framework.

cs.AI↗

arXiv2022

Investigating Transfer Learning in Graph Neural Networks

Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.

cs.LG↗

arXiv2021

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. Our approach leverages the compositionality of both value functions and language, with the aim of reducing the sample complexity of learning novel tasks. First, we train a reinforcement learning agent to learn value functions that can be subsequently composed through a Boolean algebra to solve novel tasks. Second, we fine-tune a seq2seq model pretrained on web-scale corpora to map language to logical expressions that specify the required value function compositions. Evaluating our agent in the BabyAI domain, we observe a decrease of 86% in the number of training steps needed to learn a second task after mastering a single task. Results from ablation studies further indicate that it is the combination of compositional value functions and language representations that allows the agent to quickly generalize to new tasks.

cs.LG↗

arXiv2020

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. In this work, we formalise the logical composition of tasks as a Boolean algebra. This allows us to formulate new tasks in terms of the negation, disjunction and conjunction of a set of base tasks. We then show that by learning goal-oriented value functions and restricting the transition dynamics of the tasks, an agent can solve these new tasks with no further learning. We prove that by composing these value functions in specific ways, we immediately recover the optimal policies for all tasks expressible under the Boolean algebra. We verify our approach in two domains---including a high-dimensional video game environment requiring function approximation---where an agent first learns a set of base skills, and then composes them to solve a super-exponential number of new tasks.

cs.LG↗

arXiv2020

Learning Options from Demonstration using Skill Segmentation

We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills using nonparametric Bayesian clustering and a reward function for each segment is then learned using inverse reinforcement learning. From this, a set of inferred trajectories for the demonstration are generated. Option initiation sets and termination conditions are learned from these trajectories using the one-class support vector machine clustering algorithm. We demonstrate our method in the four rooms domain, where an agent is able to autonomously discover usable options from human demonstration. Our results show that these inferred options can then be used to improve learning and planning.

cs.LG↗

arXiv2020

Quantisation and Pruning for Neural Network Compression and Regularisation

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks through network pruning and quantisation. We examine their efficacy on large networks like AlexNet compared to recent compact architectures: ShuffleNet and MobileNet. Our results show that pruning and quantisation compresses these networks to less than half their original size and improves their efficiency, particularly on MobileNet with a 7x speedup. We also demonstrate that pruning, in addition to reducing the number of parameters in a network, can aid in the correction of overfitting.

cs.LG↗

arXiv2020

Inter- and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition

Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then retraining on a new one is called transfer learning. In this paper we analyse the effectiveness of using deep transfer learning for character recognition tasks. We perform three sets of experiments with varying levels of similarity between source and target tasks to investigate the behaviour of different types of knowledge transfer. We transfer both parameters and features and analyse their behaviour. Our results demonstrate that no significant advantage is gained by using a transfer learning approach over a traditional machine learning approach for our character recognition tasks. This suggests that using transfer learning does not necessarily presuppose a better performing model in all cases.

cs.LG↗

arXiv2019

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. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent that, when grounded with problem-specific information, are provably sufficient for planning. We demonstrate transfer in two different domains, where an agent learns a portable, task-independent symbolic vocabulary, as well as rules expressed in that vocabulary, and then learns to instantiate those rules on a per-task basis. This reduces the number of samples required to learn a representation of a new task.

cs.LG↗

arXiv2018

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. In general, however, it is unclear how to compose skills in a principled way. We provide a "recipe" for optimal value function composition in entropy-regularised reinforcement learning (RL) and then extend this to the standard RL setting. Composition is demonstrated in a video game environment, where an agent with an existing library of policies is able to solve new tasks without the need for further learning.

cs.LG↗