Simple policy search outperforms advanced learnable test-time augmentation techniques.
problem Improving predictive performance through test-time data augmentation.
method Greedy policy search (GPS) for learning test-time augmentation policies.
result Augmentation policies learned with GPS achieve superior predictive performance and robustness.
PBA generates nonstationary augmentation schedules to match AutoAugment's performance with less compute.
problem Choosing an effective augmentation policy from a large search space.
method Population Based Augmentation (PBA) generates nonstationary augmentation policy schedules.
result PBA matches AutoAugment's performance on CIFAR-10, CIFAR-100, and SVHN with less compute.
Stabilizes policy optimization with off-policy data using divergence augmentation.
problem Premature convergence and instability in policy optimization with off-policy data.
method Incorporates Bregman divergence between behavior and current policies to ensure safe policy updates.
result Empirically shows better performance in data-scarce scenarios compared to other algorithms.
Study improves voice conversion model with Mel-spectrogram augmentation.
problem Insufficient speech pairs data for training sequence-to-sequence voice conversion models.
method Experimented with Mel-spectrogram augmentation using SpecAugment policies and proposed new augmentation policies.
result Time axis warping policies showed better performance in training the voice conversion model.
SapAugment learns adaptive augmentation policies for better model training.
problem Fixed data augmentation methods often apply the same augmentation to all samples, ignoring sample difficulty.
method SapAugment adapts augmentation parameters based on training loss, learning a sample-adaptive policy.
result SapAugment achieves up to 21% relative reduction in word error rate on LibriSpeech dataset.
Vision and learning have made significant progress that could improve robotics policies for complex tasks and environments. Learning deep neural networks for image understanding, however, requires large amounts of domain-specific visual data. While collecting such data from real robots is possible, such an approach lim…
Entropy regularization improves policy optimization in reinforcement learning.
problem Improving policy optimization in reinforcement learning.
method Entropy regularization is introduced to soften the greedy policy towards a more diverse softmax policy, leading to a continuously parameterized algorithm that interpolates between policy gradient and Q-learning.
result An intermediate algorithm can improve performance in reinforcement learning.
CODA resolves coordination issues in offline multi-agent reinforcement learning.
problem Coordination failure in offline multi-agent reinforcement learning.
method Diffusion-based multi-agent trajectory generator for data augmentation.
result CODA resolves coordination pathologies in continuous polynomial games and complex benchmarks.
Enhances reinforcement learning from sparse data.
problem Limited data for offline reinforcement learning.
method Trajectory-based data augmentation.
result Improves reinforcement learning performance.
Adversarial AutoAugment improves image classification with less computation.
problem Improving deep neural network generalization through data augmentation.
method Adversarial method to optimize augmentation policies without retraining the target network.
result Significant performance improvements on ImageNet and CIFAR-10.
Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implement…
Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative to previous baseline estimators on tasks with binary action space, inspired by …
This paper improves auto-augment efficiency by sharing augmentation weights.
problem Efficient evaluation of augmentation policies for model training.
method Augmentation-Wise Weight Sharing (AWS) to create a fast yet accurate proxy task.
result Augmentation policies found achieve superior accuracies compared to existing methods.
Optimizes wireless network resource management with state-augmented policies.
problem Optimizing network-wide utility with user performance constraints.
method State-augmented parameterization of RRM policy, using dual variables.
result Superior trade-off between mean, minimum, and 5th percentile rates.
The paper uses potential functions to help reinforcement learning agents learn optimal policies.
problem Learning optimal stochastic policies in reinforcement learning.
method Augmenting the reward with potential functions and applying these to policy gradient algorithms.
result Potential-based reward shaping preserves optimality of stochastic policies and speeds up learning.
BO-Aug automates data augmentation for image classification tasks.
problem Designing optimal data augmentation policies is time-consuming and costly.
method Bayesian optimization for finding optimal data augmentation policies.
result BO-Aug achieves state-of-the-art classification accuracy.
Fast AutoAugment speeds up data augmentation search.
problem Efficiently searching for effective data augmentation policies.
method Density matching-based search strategy.
result Comparable performance with faster search time.
Greedy AutoAugment improves accuracy with less computation.
problem Finding effective data augmentation policies to cover the search space.
method Greedy approach to reduce the number of trials from exponential to linear growth.
result Greedy AutoAugment increases accuracy by 360 times with fewer resources.
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …
New measures quantify how data augmentation improves model performance.
problem Understanding the effectiveness of data augmentation in deep learning.
method Introduced Affinity and Diversity measures to quantify augmentation performance.
result Augmentation performance is best achieved by optimizing both Affinity and Diversity.
This work extends ME-RL using diffusion models to sample optimal policies.
problem Sampling from the optimal policy trajectory distribution in ME-RL.
method Introducing Diffusion-Augmented Markov Decision Processes (DA-MDPs) to minimize reverse KL divergence.
result DA-MDPs enable seamless integration into various ME-RL methods and outperform baselines.
Enhances RL in target domains with limited data using augmented return.
problem Utilize data from an accessible source domain to improve policy learning in a target domain with scarce data.
method Return Augmented Decision Transformer (REAG) method, which augments the return in the source domain to align with the target domain's optimal trajectory distribution.
result The proposed REAG method achieves the same level of suboptimality as without a dynamics shift, enhancing DT type frameworks' performance in off-dynamics RL.
DAC combines actor-critic methods for learning options.
problem Learning hierarchical policies in reinforcement learning.
method Double Actor-Critic (DAC) architecture using two parallel augmented MDPs.
result DAC outperforms existing methods in robot simulation tasks.
Research improves open-set learning by leveraging unlabelled data.
problem Learning between observed and unobserved novel categories.
method Unified policy of positive and unlabelled learning, semi-supervised learning, and open-set recognition.
result Achieves state-of-the-art results in open-set learning.
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to inter…
A robust method for off-policy evaluation in contextual bandits.
problem Evaluating policies when direct methods are unavailable.
method Robust regression approach to off-policy evaluation.
result Superior empirical performance across benchmarks.
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each…
New methods use vector search and nearest-neighbor matching for policy learning in causal inference.
problem Learning optimal policies in causal inference with limited data.
method RAG-based policy learning with vector search and nearest-neighbor matching.
result The methods bound the within-candidate choice regret and evaluate the one-step method directly as a policy.
A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from challenges related to partial observability, combinatorial exploration spaces, path planning, and a scarc…
Improves RL from historical data by stitching trajectories.
problem Lack of high-quality data for offline RL.
method Trajectory Stitching (TS) to augment historical data with synthetic actions.
result Improves RL policy performance over baseline.
Entangled bisimulation improves policy learning from visual input.
problem Learning generalizeable policies from visual input in the presence of visual distractions.
method Proposes entangled bisimulation, a bisimulation metric for continuous state and action spaces.
result Entangled bisimulation improves policy learning on the Distracting Control Suite (DCS).
A new reinforcement learning method uses model derivatives to improve policy optimization.
problem Improving sample efficiency and performance in model-based reinforcement learning.
method Constructs an actor-critic algorithm that uses the pathwise derivative of the learned model and policy.
result Consistently more sample efficient and matches model-free algorithms' asymptotic performance.
Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the training set. The resulting explosion of the dataset size can be an issue in te…
This study shows how trade policy uncertainty affects stock-T bill correlations.
problem The impact of trade policy uncertainty on stock-T bill relationships.
method Extended Dynamic Conditional Correlation (DCC) framework incorporating exogenous variables.
result Trade policy uncertainty significantly alters stock-T bill correlations, especially under specific political conditions.
The paper provides theoretical guarantees for behavior cloning using generative models.
problem Behavior cloning of complex expert demonstrations using generative models.
method The paper proposes a theoretical framework invoking low-level controllers to stabilize imitation around expert demonstrations. It shows that with suitable low-level stability guarantees and powerful generative models, pure supervised behavior cloning can match expert trajectories.
result The paper proves that with a suitable low-level stability guarantee and a powerful enough generative model, pure supervised behavior cloning can generate trajectories matching the per-time step distribution of essentially arbitrary expert trajectories in an optimal transport cost.
Enhances pairs trading with neural networks and Kalman Filters.
problem Inaccurate linear models in pairs trading lead to suboptimal performance.
method Augments Kalman Filter with Neural Networks to improve financial indicator extraction.
result Empirically shows improved trading performance compared to benchmarks.
Study shows refugee matching gains are robust to different evaluation methods.
problem Stability of refugee matching gains under various evaluation methods.
method Used multiple off-policy evaluation methods including IPW and AIPW.
result Impact estimates remain consistent in magnitude and statistically significant.
Perry uses auxiliary data to estimate RL policy values with confidence intervals.
problem Leveraging auxiliary datasets for off-policy evaluation with uncertainty quantification.
method Two methods for constructing valid confidence intervals for OPE with data augmentation.
result Methods consistently produce confidence intervals covering ground truth policy values.
New offline RL algorithms tackle partial data coverage with optimal performance and practicality.
problem Partial data coverage in offline RL datasets.
method Augmented Lagrangian method applied to MIS formulation for optimal offline RL.
result Statistically optimal offline RL with practical performance, eliminating conservatism.
New insights into data augmentation for improving robustness in computer vision.
problem Challenges in achieving robustness to distributional shift in computer vision.
method Investigation of trade-offs between robustness to high and low frequency corruptions using Gaussian data augmentation and adversarial training.
result Improvements in robustness to high frequency corruptions come at the cost of reduced robustness to low frequency corruptions.
Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance yet challenging. There has been little theoretical analysis of this problem. In…
State-augmented algorithm optimizes wireless network resource management.
problem Optimizing resource allocation in multi-user wireless networks.
method Proposes a state-augmented algorithm using dual variables.
result Feasible and near-optimal resource decisions achieved.
ReMixMatch improves semi-supervised learning with new techniques for data efficiency.
problem Improving semi-supervised learning with limited labeled data.
method Distribution alignment and augmentation anchoring with AutoAugment.
result Significantly more data-efficient, requiring less labeled data for similar accuracy.
We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization ta…
A novel fully asynchronous scheme for distributed reinforcement learning over networks.
problem Policy evaluation in distributed reinforcement learning over networks.
method Design of a stochastic average gradient (SAG) based distributed algorithm and push-pull augmented graph approach.
result The proposed algorithm converges at a linear rate of \(\mathcal{O}(c^k)\) with \(c\in(0,1)\) and \(k\) increasing by one per node update.
New RL method learns policies from few data using causal models.
problem Limited interaction data and heterogeneous patient responses.
method Exploits structural causal models to model state dynamics and counterfactual reasoning.
result Counterfactual RL algorithms converge to optimal value function.
Patch Gaussian augmentation improves model robustness without sacrificing accuracy.
problem Challenges in building robust models without sacrificing accuracy.
method Adds Gaussian noise to randomly selected patches in images.
result Achieves state-of-the-art performance on benchmarks while improving clean data accuracy.
In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task learning. We propose to adapt and reuse the mapped source task optimal-policy directly …