ReaPER improves learning efficiency by prioritizing reliable experiences.
problem Inefficient sampling of past experiences in reinforcement learning.
method Introducing a novel measure of reliability to prioritize experiences in PER.
result ReaPER outperforms PER in various environments, including Atari-10.
Reverse Experience Replay improves Deep Q-learning for sparse rewards.
problem Sparse rewards and reward-maximizing tasks in Deep Q-learning.
method Sampling transitions in reverse order for training.
result Significantly increased performance in tasks with limited experience and memory capacity.
Algorithm creates synthetic experiences to enhance Deep Reinforcement Learning.
problem Lack of synthetic experiences in classic Experience Replay.
method Bootstraps synthetic experiences to augment the replay memory.
result Synthetic experiences can improve learning speed and performance.
A new method prioritizes and recycles experiences for better reinforcement learning.
problem Improving reinforcement learning efficiency by prioritizing and recycling experiences.
method Double-prioritized state-recycled (DPSR) experience replay.
result DPSR achieved state-of-the-art results in Atari games, outperforming original and prioritized methods.
Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past. In an effort to learn more efficiently, researchers proposed prioritized experience replay (PER) which samples important transitions more frequently. In this paper, we propo…
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize a rule-based replay strategy, which may be sub-optimal. In this work, we consid…
Efficient actor-critic learning with shared experience replay improves data efficiency.
problem Challenges in actor-critic reinforcement learning with experience replay and off-policy learning stability.
method Combining actor-critic algorithms with shared experience replay, analyzing V-trace, proposing a trust region scheme.
result State-of-the-art data efficiency on Atari achieved with 200M environment frames.
AES improves policy gradient performance by adaptively selecting experience.
problem High variance in gradient estimators from past trajectories.
method AES learns an adaptive sampling distribution to minimise gradient variance.
result AES leads to significantly improved performance in continuous control tasks.
This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these techniques with DDPG and DQN methods. CER always adds the most recent experience to th…
IMeL turns RL into SL by interpolating improved experiences.
problem Improving reinforcement learning efficiency and scalability.
method IMeL uses a reservoir of experiences and a NN regressor for interpolation.
result IMeL achieves preliminary results and proposes itself as a baseline.
ER-GNN uses experience replay to prevent GNNs from forgetting previous tasks.
problem Catastrophic forgetting in GNNs when learning multiple tasks sequentially.
method Experience Replay framework to store and replay knowledge from previous tasks.
result ER-GNN effectively mitigates catastrophic forgetting in GNNs.
Paper uses transfer learning and Bayesian optimization to reduce DNA sequence design experiments.
problem Designing many similar DNA sequences for specific applications is expensive and time-consuming.
method Combines transfer learning with Bayesian optimization to reduce experiment count.
result Total number of experiments can be significantly reduced by sharing information between tasks.
CEA augments reinforcement learning by generating counterfactual experiences.
problem Challenges in reinforcement learning, especially out-of-distribution and inefficient exploration.
method CEA uses variational autoencoders to model state transitions and introduces randomness for non-stationarity. It expands learning data through counterfactual inference.
result CEA outperforms SOTA algorithms in diverse environments.
The paper improves reinforcement learning stability and efficiency with a new theoretical framework.
problem Stability and efficiency in reinforcement learning, especially in data-scarce scenarios.
method Theoretical framework using resampled U- and V-statistics to model experience replay, applied to policy evaluation and kernel ridge regression. result Significant improvements in stability and efficiency, particularly in data-scarce scenarios.
New insights into experience replay in RL algorithms.
problem Understanding the impact of replay capacity and replay ratio in Q-learning.
method Systematic and extensive analysis of experience replay in Q-learning methods, focusing on replay capacity and replay ratio.
result Greater replay capacity significantly improves performance for certain algorithms, while other techniques offer limited benefit.
Machine learning boosts physics research, especially at high energy experiments.
problem Finding new fundamental physics in high energy experiments.
method Review of machine learning methods and applications in high energy physics.
result Modern machine learning techniques have expanded the scope of physics research.
Experiments used in current continual learning research do not faithfully assess fundamental challenges of learning continually. Instead of assessing performance on challenging and representative experiment designs, recent research has focused on increased dataset difficulty, while still using flawed experiment set-ups…
Experience reuse is key to sample-efficient reinforcement learning. One of the critical issues is how the experience is represented and stored. Previously, the experience can be stored in the forms of features, individual models, and the average model, each lying at a different granularity. However, new tasks may requi…
We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with respect to multiple experiments, and their related data distributions. Each collected sample is associat…
Inertial confinement fusion (ICF) experiments are designed using computer simulations that are approximations of reality, and therefore must be calibrated to accurately predict experimental observations. In this work, we propose a novel nonlinear technique for calibrating from simulations to experiments, or from low fi…
Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off …
Despite huge success, deep networks are unable to learn effectively in sequential multitask learning settings as they forget the past learned tasks after learning new tasks. Inspired from complementary learning systems theory, we address this challenge by learning a generative model that couples the current task to the…
Experience replay is a key technique behind many recent advances in deep reinforcement learning. Allowing the agent to learn from earlier memories can speed up learning and break undesirable temporal correlations. Despite its wide-spread application, very little is understood about the properties of experience replay. …
RER improves sample complexity by updating in reverse order.
problem Theoretical analysis limits RER's convergence rate.
method Tighter analysis for larger learning rates and longer sequences.
result RER converges faster with larger learning rates and longer sequences.
Synthetic experiments are crucial for assessing causal machine learning methods.
problem Current empirical evaluations of causal machine learning methods are insufficient and unreliable.
method Propose principles for conducting rigorous empirical analyses with synthetic data.
result Rigorous synthetic experiments are essential for building trust in causal machine learning methods.
Machine learning experiments often contain errors, especially in confusion matrices and statistical tests.
problem Errors in machine learning experiments, particularly in confusion matrices and statistical tests.
method Analyzed 49 papers describing 2456 experiments, checking for errors in confusion matrices and statistical significance.
result 22 out of 49 papers contain demonstrable errors, with 7 statistical and 16 related to confusion matrix inconsistency.
Algorithm learns new tasks efficiently from past experience.
problem Lack of robustness to distributional shift in meta-reinforcement learning.
method Model Identification and Experience Relabeling (MIER) using dynamics models.
result Efficient extrapolation to out-of-distribution tasks.
Machine learning experiments often mislead due to unmet assumptions.
problem Machine learning experiments with pooled data may not meet necessary assumptions for unbiased causal effect estimation.
method Analysis of assumptions required for unbiased causal effect estimation in machine learning experiments.
result Practical applications of A/B-tests with machine learning models may not yield unbiased estimates of causal effect.
Machine learning, specifically LSTM, models quantum experiments efficiently.
problem Modeling complex quantum states with high-dimensional entanglement.
method Used a long short-term memory (LSTM) neural network to predict quantum experiment outcomes.
result LSTM neural networks can accurately predict quantum experiment outcomes without computing the states themselves.
GBS uses machine learning to design products based on consumer preferences.
problem Designing products to meet consumer preferences.
method GBS is a discrete choice experiment that uses machine learning to adaptively construct paired comparison questions.
result GBS outperforms existing methods in accuracy and sample efficiency.
VRER selectively reuses past observations to reduce variance in policy optimization.
problem Lack of effective experience replay for accelerating policy optimization in complex systems.
method Variance Reduction Experience Replay (VRER) framework that selectively reuses informative samples.
result VRER reduces gradient variance and improves policy learning over state-of-the-art algorithms.
A-ICP selects experiments to learn causal effects efficiently.
problem Learning causal effects from observational data is difficult.
method Active learning framework based on Invariant Causal Prediction.
result Proposes intervention selection policies to reveal direct causes.
ORIL learns a reward function from unlabeled data to improve robot learning.
problem Leveraging unlabeled data for robot learning.
method ORIL learns a reward function from demonstrator and unlabeled trajectories, annotates data, and trains an agent via offline reinforcement learning.
result ORIL consistently outperforms BC agents on various robotic tasks.
How useful can machine learning be in a quantum laboratory? Here we raise the question of the potential of intelligent machines in the context of scientific research. A major motivation for the present work is the unknown reachability of various entanglement classes in quantum experiments. We investigate this question …
Automated PDE discovery from multiple noisy experiments.
problem Inherent variability in experiments makes single experiment inference unreliable.
method Randomised adaptive group Lasso sparsity estimator in deep learning framework.
result More generalizable PDEs found from multiple datasets.
Online field experiments are the gold-standard way of evaluating changes to real-world interactive machine learning systems. Yet our ability to explore complex, multi-dimensional policy spaces - such as those found in recommendation and ranking problems - is often constrained by the limited number of experiments that c…
The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments. It can be easily extended and specialized and it is a…
Unsupervised machine learning helps design complex experiments more efficiently.
problem Designing experiments with many factors and constraints is challenging and costly.
method Applied a beta variational autoencoder (beta-VAE) to represent trials in a low-dimensional latent space.
result Generated pragmatic designs with fewer trials while maintaining objectives.
Method improves treatment effect estimation in randomized experiments.
problem Estimating distributional treatment effects in randomized experiments.
method Distributional regression framework with machine learning for variance reduction.
result The proposed method reduces variance of distributional treatment effect estimators.
This paper presents a method to improve continual learning stability and plasticity.
problem Balancing learning stability and plasticity in deep learning.
method Batch-level Experience Replay with Review approach.
result Achieved 1st place in all three scenarios of the CVPR 2020 CLVision challenge.
We address the problem of retrieving relevant experiments given a query experiment, motivated by the public databases of datasets in molecular biology and other experimental sciences, and the need of scientists to relate to earlier work on the level of actual measurement data. Since experiments are inherently noisy and…
Algorithm selects optimal experiments in Markov chains to learn unknown quantities.
problem Designing efficient experiments in Markov chains to learn about unknown quantities.
method Proposes extsc{markov-design} algorithm for sequential policy selection.
result Algorithm provably converges to optimal measurement allocation.
Flower framework simplifies federated learning experiments on edge devices.
problem Realistic implementation of Federated Learning on edge devices is challenging.
method Developed a comprehensive federated learning framework, Flower, supporting large-scale experiments on heterogeneous devices.
result Flower enables federated learning experiments with up to 15M client size using only two high-end GPUs.
The results from most machine learning experiments are used for a specific purpose and then discarded. This results in a significant loss of information and requires rerunning experiments to compare learning algorithms. This also requires implementation of another algorithm for comparison, that may not always be correc…
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
Bayesian Experience Reuse improves learning from multiple experts.
problem Learning from multiple experts with conflicting goals.
method Bayesian neural networks with shared features to model uncertainty and derive a probability distribution over expert models.
result BERS method effectively samples demonstrations from the derived distribution to reuse them in new tasks.
In this paper, we consider the problem of malware detection and classification based on image analysis. We convert executable files to images and apply image recognition using deep learning (DL) models. To train these models, we employ transfer learning based on existing DL models that have been pre-trained on massive …
The field of deep learning is experiencing a trend towards producing reproducible research. Nevertheless, it is still often a frustrating experience to reproduce scientific results. This is especially true in the machine learning community, where it is considered acceptable to have black boxes in your experiments. We p…