A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper discusses flaws in traditional RL for lifelong learning.
New method for RL tasks transfer using Lipschitz continuity.
Modulating masks improve lifelong reinforcement learning.
Develops RL algorithm for lifelong non-stationary environments.
Algorithm learns multiple tasks with minimal planning, achieving near-optimal performance.
Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of biological memory transfer to arrive at AI algorithms for memory consolidation and repl…
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 exten…
Framework for lifelong learning using eigentasks to avoid forgetting and transfer knowledge.
Dynamic information balancing reduces catastrophic forgetting in modular neural networks.
PAC-Bayesian analysis improves lifelong learning in multi-armed bandits.
New method speeds up lifelong learning of complex tasks.
In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime to improve its ability to solve new problems. We argue that previous experience…
Top 8 robotic vision systems tackled lifelong object recognition challenges.
Pre-trained language model boosts RL efficiency.
Paper proposes an algorithm for lifelong learning with shared structure.
Paper converts graph learning to lifelong learning.
Flatland is a simple, lightweight environment for fast prototyping and testing of reinforcement learning agents. It is of lower complexity compared to similar 3D platforms (e.g. DeepMind Lab or VizDoom), but emulates physical properties of the real world, such as continuity, multi-modal partially-observable states with…
Algorithm captures and refines features for efficient lifelong learning.
Builds a novel educational recommender for lifelong learners.
A simple approach improves performance on both past and future tasks in lifelong learning.
Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent neural networks. To evaluate the models in the lifelong learning setting, we propo…
New dataset and benchmarks for lifelong robotic vision tasks.
Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor sk…
We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a Differentiable Neural Computer (DNC). The agent and DNC model are trained in conjunction iteratively. The agent improves its policy in simu…
DBULL learns new clusters without forgetting past knowledge in streaming unlabelled data.
Transfer learning has received a lot of attention in the machine learning community over the last years, and several effective algorithms have been developed. However, relatively little is known about their theoretical properties, especially in the setting of lifelong learning, where the goal is to transfer information…
Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights. However, the knowledge libraries or deep networks for most recent lifelong learning models are with prescribed size, and can degenerate the …
Framework for lifelong learning of compositional structures.
New framework SEU solves lifelong learning's catastrophic forgetting issue.
New schemes improve lifelong learning by balancing old and new tasks.
A Boolean algebra formalizes task composition for reinforcement learning.
Unified framework supports lifelong learning properties.
Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong …
Graphs evolve; GNNs learn from past tasks.
Adapts Lifelong Learning for Federated Learning to prevent model drift.
In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set…
AOP combines model-based planning with model-free learning to handle lifelong learning challenges.
Learning from prior tasks and transferring that experience to improve future performance is critical for building lifelong learning agents. Although results in supervised and reinforcement learning show that transfer may significantly improve the learning performance, most of the literature on transfer is focused on ba…
Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends standard Q-learning to a two-stream model for processing positive and negative rewards, and allows to incorporate a wide range of reward-proce…
Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning makes a batch processing of each task, implying that a data collection step is requi…
In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards…
PETAL adapts models to changing target domains over time.
Automatic Machine Learning (Auto-ML) systems tackle the problem of automating the design of prediction models or pipelines for data science. In this paper, we present Lifelong Bayesian Optimization (LBO), an online, multitask Bayesian optimization (BO) algorithm designed to solve the problem of model selection for data…
Algorithm integrates uncertainty for lifelong learning in dynamic environments.
The paper tackles lifelong learning in multi-armed bandits, aiming to minimize average regret over multiple tasks.
A model for deciding which facts to remember in a lifelong learning scenario.
We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018. This data driven competition asked participants to develop computer programs capable of solving supervised learning problems where the i.i.d. assumption did not hold. Large data sets w…
The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or continual fashion. Current solutions to the continual learning problem require experie…