Unified study of stateful replay for streaming learning, reducing forgetting by 2-3x.
problem Catastrophic forgetting in streaming generative and predictive learning.
method Unified analysis of stateful replay for autoencoding, forecasting, and classification tasks.
result Stateful replay reduces average forgetting by a factor of 2-3 on heterogeneous multi-task streams.
Model forgets examples; this research predicts which ones to replay.
problem Language models forget examples during updates, leading to errors.
method Train forecasting models to predict which examples will be forgotten.
result Forecasting models can reduce forgetting of upstream pretraining examples.
A novel framework optimizes experience replay for reinforcement learning.
problem Optimizing the replay policy for better performance in off-policy reinforcement learning.
method Proposes a novel ERO framework that alternately updates the agent policy and replay policy.
result Demonstrates improved performance in various continuous control tasks.
A new algorithm for non-stationary contextual bandits with optimal dynamic regret.
problem Non-stationary contextual bandits with unknown switching frequency and data distribution variation.
method Parameter-free, efficient, and optimal algorithm using replay phases to detect non-stationarity.
result Achieves dynamic regret O ( min { S T , Δ 1 3 T 2 3 } ) \mathcal{O}(\min\{\sqrt{ST}, Δ^{\frac{1}{3}}T^{\frac{2}{3}}\}) O ( min { S T , Δ 3 1 T 3 2 }) . 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.
New modifiers improve noisy RNN replay in hippocampal networks.
problem Improving noisy RNN replay in hippocampal networks.
method Three approaches: hidden state leakage, adaptation, and momentum.
result Hidden state leakage, adaptation, and momentum improve noisy RNN replay.
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.
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…
We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another replay-based continual learning paradigm (which we term "marginal rep…
Curious Replay improves model-based reinforcement learning agents' adaptability.
problem Existing model-based reinforcement learning agents struggle to adapt quickly to changing environments.
method Curious Replay uses a curiosity-based priority signal for prioritized experience replay tailored to model-based agents.
result Agents using Curious Replay achieve improved performance in exploration and on benchmarks.
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.
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.
In this paper, we propose a replay attack spoofing detection system for automatic speaker verification using multitask learning of noise classes. We define the noise that is caused by the replay attack as replay noise. We explore the effectiveness of training a deep neural network simultaneously for replay attack spoof…
Combines experience replay and exploration for better agent performance.
problem Improving exploration efficiency and robustness in reinforcement learning.
method Integrates Intrinsic Rewards with Prioritized Oversampled Experience Replay (POER).
result Achieves better agent performance and sample efficiency compared to PPO/RND.
Generative replay improves continual learning by using generated data as negative examples.
problem Catastrophic forgetting in continual learning.
method Using generative models to provide negative examples for new classes.
result Generative replay can improve learning new classes even when existing approaches fail.
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.
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 U U - and V V 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.
A new method for prioritizing sequences in reinforcement learning improves learning efficiency.
problem Efficient learning in reinforcement learning algorithms.
method Prioritized Sequence Experience Replay (PSER) for prioritizing sequences of experience.
result PSER is guaranteed to converge faster than PER and substantially improves performance.
A new method improves continual learning by replaying pseudo data and using orthogonal weight modification.
problem Catastrophic forgetting in class incremental learning.
method Generative replay with orthogonal weight modification.
result Our method achieves substantial improvement over conventional generative replay and OWM.
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 memory replay mechanism improves reinforcement learning stability and speed.
problem Forgetting in reinforcement learning with continuous control.
method Augmented Memory Replay (AMR) that optimizes the replay of past experiences.
result AMR enhances stability and convergence speed of learning algorithms.
Prototype-based generative replay framework for online continual regression.
problem Addressing the challenge of non-stationary data streams in regression tasks.
method Adaptive output-space discretization model for prototype-based generative replay.
result Reduces forgetting and provides more stable performance.
New framework models echo chamber learning, proving tight bounds on algorithm performance.
problem Echo chambers in machine learning where systems learn from self-annotated data.
method Online Learning in the Replay Setting, Extended Threshold dimension, closure-based learner.
result Proves tight bounds on algorithm performance against replay adversaries.
New method retrieves most interfered samples for continual learning.
problem Challenges in continual learning with online data streams.
method Controlled sampling of most interfered samples for replay.
result Consistent gains in performance and reduced forgetting.
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. …
The study explores when parametric models enhance reinforcement learning, validating a hypothesis on Atari games.
problem When and how to use parametric models in reinforcement learning.
method Comparison of parametric models and experience replay, validating a hypothesis on Atari games.
result Replay-based algorithms can be competitive or superior to model-based algorithms under suitable conditions.
Paper proposes D3M to improve anti-spoofing detection by balancing loss function and using complementary features.
problem Improving automatic speaker verification systems against high-quality playback attacks.
method D3M uses a balanced focal loss function to dynamically scale loss based on sample traits, and combines three feature types for robust detection.
result D3M systems outperform conventional methods significantly, achieving min-tDCF of 0.0124 and EER of 0.55%.
Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the accuracy of such updates may deteriorate when the policy diverges from past behavio…
LiDER refreshes past experiences in RL by dreaming about them.
problem Improving data efficiency in off-policy RL algorithms.
method Refreshing past experiences in a replay buffer using the current policy.
result LiDER consistently improves performance in Atari games.
Modern Hopfield networks help prevent forgetting in generative models after task changes.
problem How to prevent forgetting in generative models after task changes.
method Introduce intrinsic forgetting as an increase in Hopfield energy after task change, analyze memory replay effectiveness, and validate predictions in experiments.
result High-energy, outlier-like samples are more forgettable than cluster-like samples, and energy-based selection of replay samples mitigates forgetting.
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.
Improves sparse reinforcement learning efficiency with OYMB.
problem Sparse rewards hinder reinforcement learning performance.
method Introduces OYMB, a sampler for HER to control minibatch makeup.
result HER combined with OYMB leads to faster real goal completion.
Latent Replay reduces continual learning computation and storage needs.
problem Catastrophic forgetting in continual learning.
method Store activations volumes at intermediate layers instead of past data, slow down learning below the latent replay layer.
result Latent Replay achieves state-of-the-art performance on complex video benchmarks.
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.
Generative replay extends sound classification models to new classes without old data.
problem Incrementally refining a sound classifier with new data causes previously learned tasks to degrade.
method Developed a generative replay procedure to generate training data in place of older datasets.
result Generative replay with 4% of old data performs as well as keeping 20% of old data.
Improved RA detection with SNN outperforming baseline by 26.8% EER.
problem Improving RA detection systems' generalizability and discriminability.
method Multi-task learning with Siamese Neural Networks (SNN) and additional reconstruction loss.
result SNN outperforms baseline by 26.8% EER, and further improvement by 13.8% with reconstruction loss.
A multi-agent simulator evaluates trading strategies using Market Replay and Interactive Agent-Based Simulation.
problem Evaluate trading strategies using Market Replay and Interactive Agent-Based Simulation.
method Multi-agent simulator for Market Replay and Interactive Agent-Based Simulation.
result IABS provides a more realistic market environment for evaluating trading strategies.
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.
Optimized RL algorithms perform well on offline datasets, outperforming fully trained agents.
problem Improving reinforcement learning performance on offline datasets.
method Random Ensemble Mixture (REM) algorithm for Q-learning, trained on DQN replay dataset.
result Offline REM outperforms strong RL baselines and fully trained DQN agent.
Improved Politex algorithm reduces regret bound to O(√T) with experience replay.
problem Learning in infinite-horizon MDPs with function approximation.
method Sharpened regret analysis of Politex algorithm, experience replay implementation.
result First high-probability O(√T) regret bound for computationally efficient algorithm.
New method improves deep RL by combining emphatic weightings with replay data.
problem Improving sample efficiency and scaling model-free RL methods.
method Developed a multi-step emphatic weighting and time-reversed n n n -step TD learning algorithm. result The new approach reduces variance and provides convergence guarantees.
Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer. Hindsight experience replay (HER) was recently proposed to tackle…
A new buffer system improves continual learning in RL agents by adapting to changing environments.
problem Improving RL agents' ability to learn from changing environments over time.
method Multi-timescale replay buffer combined with invariant risk minimization.
result The method shows improvement over baselines in continual learning settings.
An attacker may use a variety of techniques to fool an automatic speaker verification system into accepting them as a genuine user. Anti-spoofing methods meanwhile aim to make the system robust against such attacks. The ASVspoof 2017 Challenge focused specifically on replay attacks, with the intention of measuring the …
Framework uses experience replay to prevent deep networks from forgetting past tasks.
problem Deep networks forget past tasks after learning new ones in sequential multitask learning.
method Generative model that couples current task with past learned tasks through a discriminative embedding space.
result Framework learns a shared abstract distribution across all tasks, preventing catastrophic forgetting.
A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods for alleviating catastrophic forgetting are currently being proposed, but diffe…
Self-supervised method detects replay spoofing using acoustic configurations.
problem Challenges in collecting large-scale datasets for replay spoofing detection.
method Self-supervised pretraining of acoustic configurations using existing datasets.
result The method outperforms baseline by 30% on ASVspoof 2019 physical access dataset.
Dual memory improves reinforcement learning efficiency.
problem Training inefficiency in reinforcement learning.
method Introduces a dual memory structure with a main and cache memory.
result Dual memory structure leads to higher scores in reinforcement learning environments.