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.
The paper proposes a method to learn from both simulation and real-world data.
problem Training autonomous systems in simulation and applying them to real-world environments.
method Balancing samples from simulation and real-world data using a replay buffer.
result The method achieves better performance in real-world tasks compared to training only in simulation.
MER algorithm speeds up VI solving with Markovian data.
problem Solving stochastic variational inequalities with Markovian data.
method MER algorithm using multi-scale sampling from a Markovian buffer.
result Achieves faster convergence without knowing Markov chain mixing time.
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.
In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biase…
A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the p…
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.
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…
DAC enhances exploration in reinforcement learning with entropy regularization.
problem Improving exploration efficiency in reinforcement learning.
method Sample-aware entropy regularization using replay buffer action distributions.
result DAC significantly outperforms existing algorithms in reinforcement learning tasks.
A distributed system identification method for LTI systems using reverse experience replay.
problem Online system identification of LTI systems over multi-agent networks.
method DSGD-RER, a distributed variant of SGD-RER with backward updates.
result The estimation error decreases as the network size grows.
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer o…
ETGL-DDPG improves DDPG for sparse reward control with new exploration and replay techniques.
problem Sparse reward continuous control in reinforcement learning.
method Introduces εt-greedy search and GDRB framework for efficient exploration and reward use. result ETGL-DDPG outperforms DDPG and other methods on sparse-reward continuous benchmarks.
Improved diffusion models for sampling from given distributions.
problem Training diffusion models to sample from a given distribution.
method Benchmarked and improved off-policy methods for diffusion sampling.
result A novel exploration strategy improves sample quality.
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.
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.
Proposes a new policy gradient algorithm to improve reinforcement learning efficiency and stability.
problem Inefficiency and instability of DDPG in practical applications, and difficulty in controlling Q estimation bias and variance.
method Introduces a Regularly Updated Deterministic (RUD) policy gradient algorithm.
result The RUD algorithm makes better use of new data and has lower Q value variance, leading to improved performance.
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. …
New algorithm optimizes linear system estimation from single trajectory.
problem Estimating LTI systems from a single trajectory.
method SGD with Reverse Experience Replay (SGD−RER) result Optimal guarantees for parameter and prediction errors.
Paper improves online time series forecasting by combining natural gradient and robust t-distribution.
problem Online time series forecasting challenges in rapidly adapting to evolving data.
method Reframed neural network optimization as a parameter filtering problem, using natural gradient and Student's t likelihood.
result Natural Score-driven Replay (NatSR) achieves stronger forecasting performance than state-of-the-art methods.
Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade on old tasks when trained successively on new tasks with different data distrib…
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many benefits, such as ability to evaluate each resulting policy. However, they usually d…
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.
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-step TD learning algorithm. result The new approach reduces variance and provides convergence guarantees.
Study improves neural network performance in sequential learning for image classification.
problem Improving neural network performance in sequential learning for image classification.
method Evaluation of approaches for computing prequential description lengths, proposing forward-calibration and replay-streams.
result Improved description lengths for image classification datasets, outperforming previous results.
A new method for generating replay samples on the fly, optimizing for not forgetting.
problem Addressing the issue of forgetting in neural networks.
method Generates auxiliary samples on the fly using the model's implicit memory, specialized to each real training batch.
result Optimizing for not forgetting leads to more efficient and scalable generation of specialized samples.
NERS improves RL by sampling diverse transitions considering local and global contexts.
problem Sampling biases in experience replay lead to redundant transitions.
method Neural Experience Replay Sampler (NERS) that considers both local and global contexts.
result NERS significantly improves RL performance by sampling diverse and meaningful transitions.
Paper proposes a new method to select memory data for online class-incremental learning.
problem Selecting which buffered images to replay for online class-incremental learning.
method Adversarial Shapley value scoring method to preserve latent decision boundaries.
result Proposed ASER method provides competitive or improved performance compared to state-of-the-art methods.
A simple technique improves continual learning by 50% on image datasets.
problem Challenges in training neural networks on a stream of shifting data.
method Experience Replay (ER) with five tricks to mitigate its shortcomings.
result ER, enhanced with tricks, achieves significant accuracy gains.
New method improves continual learning by anchoring past knowledge.
problem Catastrophic forgetting in continual learning.
method Bilevel optimization to update current task knowledge while keeping past task predictions.
result Improves accuracy and forgetting metrics compared to experience replay.
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as …
Study compares SPG and PPO for racing games, finding SPG more stable with weighted actions.
problem Training continuous action reinforcement learning algorithms for racing games.
method Introduced novel racing environment, tested SPG and PPO with modifications and experience replay.
result Experience replay not beneficial for PPO in continuous action spaces, SPG more stable with weighted actions.
New method improves ABI for sequential data, reducing forgetting and improving accuracy.
problem Performance degradation of ABI under model misspecification and distribution shifts.
method Decouples simulation-based pre-training from unsupervised SC fine-tuning, using memory buffer and elastic weight consolidation.
result Significant mitigation of forgetting and improved posterior estimates compared to standard simulation-based training.
Although reinforcement learning has made great strides recently, a continuing limitation is that it requires an extremely high number of interactions with the environment. In this paper, we explore the effectiveness of reusing experience from the experience replay buffer in the Deep Q-Learning algorithm. We test the ef…
Enhances RL performance with a population-guided parallel learning scheme.
problem Improving off-policy reinforcement learning performance.
method Population-guided parallel learning scheme with shared experience replay buffer and soft policy update.
result Monotone improvement of the expected cumulative return proved theoretically and demonstrated in practice.
Optimizer memory affects learning rate sensitivity in shuffle order, impacting fine-tuning noise.
problem Optimizer memory affects the learning rate sensitivity in shuffle order, leading to fine-tuning noise.
method Isolated the mechanism of fixed-clock optimizer memory affecting the learning rate sensitivity in shuffle order, deriving a fit-free way to size the noise.
result Fixed-clock optimizers like AdamW produce a larger first-order noise channel compared to memoryless optimizers, affecting fine-tuning comparisons.
Paper proposes a new method for sampling from complex distributions.
problem Sampling from unnormalised density functions in complex distributions.
method Combines amortised and particle-based methods with reinforcement learning.
result Improves sampling from complex distributions compared to existing methods.
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past traject…
Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the real world but fail to generalize to subtle variations in the underlying dynamics, e.g., due to differences in mass, friction, or actuators a…
Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the weights for the value function. In this work, we explore a resampling strategy as an alternative to reweighting. We propose Im…
In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states. The problem of learning from imbalanced data is a well-known problem in supervised…
Secure aggregation for buffered asynchronous federated learning without TEEs.
problem Privacy and convergence in buffered asynchronous federated learning.
method Developed a new protocol (BASecAgg) that ensures privacy without TEEs by carefully designing masks.
result BASecAgg achieves similar convergence guarantees as FedBuff without TEEs.
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…
Simplifies RL training with fewer techniques, reducing bias and instability.
problem Training instabilities and high sample complexity in RL.
method Introduced a simple deterministic policy gradient, used propensity estimation, and delayed policy updates.
result Improved performance and reduced sample complexity through these techniques.
We introduce a Markovian single point process model, with random intensity regulated through a buffer mechanism and a self-exciting effect controlling the arrival stream to the buffer. The model applies the principle of the Hawkes process in which point process jumps generate a shot-noise intensity field. Unlike the Ha…
An agent learning through interactions should balance its action selection process between probing the environment to discover new rewards and using the information acquired in the past to adopt useful behaviour. This trade-off is usually obtained by perturbing either the agent's actions (e.g., e-greedy or Gibbs sampli…
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.