Fiber simplifies RL and population-based methods for distributed training.
problem Challenges in RL and population-based methods, including frequent interaction with simulations and dynamic scaling.
method Introducing Fiber, a scalable distributed computing framework.
result Significantly expands accessibility of large-scale parallel computation.
Automates RL with sample-efficient hyperparameter optimization.
problem Challenges in applying deep RL due to hyperparameter sensitivity and inefficiency.
method Population-based AutoRL framework for meta-optimizing RL algorithms and architectures.
result Reduces the number of environment interactions needed for meta-optimization by up to an order of magnitude.
PB2 uses probabilistic models to efficiently discover high-performing hyperparameters.
problem Efficiently tuning hyperparameters in reinforcement learning (RL) is computationally expensive and laborious.
method Population-Based Bandits (PB2) uses probabilistic models to guide hyperparameter exploration.
result PB2 discovers high-performing hyperparameter configurations with fewer agents than PBT.
A new RL method uses flows to mix policies for better exploration.
problem Learning in high-dimensional state spaces with deceptive rewards.
method Uses normalizing flows to attract and repel policies in a population.
result Empirically outperforms Soft-Actor Critic (SAC) on MuJoCo tasks.
Robust RL improves controller robustness to dynamics variations using adversarial populations.
problem Robustness issues in RL when dynamics are perturbed.
method Adversarial population augmentation to the Robust RL formulation.
result Population-based adversarial approach yields more robust and generalizable policies.
ABPS improves RL training efficiency by sharing policies and evolving hyper-params.
problem Data inefficiency in training deep RL models for real-world applications.
method ABPS: adaptive behavior policy sharing; ABPS-PBT: hybridizing ABPS with PBT for evolving hyper-params.
result ABPS achieves superior performance and reduced variance compared to conventional hyper-parameter tuning.
Population-based learning improves representation of unstructured data.
problem Improving representation of unstructured data.
method Instantiating Lewis signaling games within a population of agents.
result Population-based learning produces better representations than single-agent learning.
Operator calculus for population-based optimization provides a unified framework for analyzing convergence of various methods.
problem Convergence analysis of population-based optimization methods
method Introduce an operator calculus for describing composite mean-field algorithms as compositions of elementary operators acting on probability measures.
result Establish a modular Lyapunov principle for certifying exponential decay of state-space Lyapunov function and search errors.
GNMC reduces XCSF population size while preserving function approximation and policy accuracy.
problem Population bloat in XCSF compaction.
method Introduced GNMC, a novel compaction algorithm.
result GNMC reduces population size significantly without compromising function approximation or policy accuracy.
New meta-optimizer learns from both point-based and population-based algorithms.
problem Current meta-optimizers are limited in space and unaware of uncertainty.
method Proposes a new meta-optimizer that learns in the space of both point-based and population-based algorithms, targeting a meta-loss function of cumulative regret and entropy.
result Empirical results show superior performance over existing competitors.
Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely …
Dynamic meta-learning improves multi-agent communication with natural language.
problem Static population-based approaches struggle with adapting to human partners using natural language.
method Dynamic population-based meta-learning approach.
result Agents outperform all prior work in communicating with seen partners and humans.
Aims to describe neural network training dynamics using two-time-scale models.
problem Lack of a general mathematical description of neural network training.
method Introduces a theoretical framework based on two-time-scale population dynamics.
result Derives selection-mutation equations and effective fitness for hyperparameters.
Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods. Inspired by the success of Deep Neuroevolution in reinforcement learning (Such et al. 2017), we explore the use of gradient-…
Current paper addresses topology issues in PBSHM to enable transfer learning.
problem Absence of meaningful topology on graph space hinders rigorous analysis.
method Introduced parametric families of structures, defined open sets, and continuous variation between fibres.
result Enabled rigorous transfer learning in PBSHM by addressing topology issues.
A new method solves graph coloring problems using gradient descent.
problem Graph coloring problems, computationally difficult.
method Population-based weight learning framework, gradient descent on GPUs.
result Improved best-known results for several large graphs.
FIRE PBT improves neural network training by focusing on long-term performance.
problem Greedy decision mechanisms in PBT lead to poor long-term performance.
method FIRE PBT uses a fitness metric to encourage long-term performance over short-term improvements.
result FIRE PBT outperforms PBT on ImageNet and matches hand-tuned learning rates.
Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each learning and acting independently to cooperate and compete with other agents, a…
Agents trained to play with themselves fail when paired with humans, suggesting the need for human-aware learning.
problem Current AI agents trained to play with themselves fail to coordinate effectively with humans.
method Introduced a simple Overcooked game environment and trained agents via self-play and population-based training. Evaluated performance against a human model.
result Agents trained to play with themselves perform poorly when paired with a human model, highlighting the need for human-aware learning.
A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches such as AutoAugment …
Study finds RNNs predict STBG better than ARIMA, useful for diabetes patients.
problem Improving short-term blood glucose prediction for diabetes management.
method Investigated Recurrent Neural Networks (RNNs) and compared them to ARIMA for STBG prediction.
result Population-based RNN model outperforms ARIMA across various prediction horizons.
In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient desc…
High-throughput 3D control training system achieves 100,000 FPS.
problem Lack of efficient, single-machine reinforcement learning systems.
method Sample Factory combines asynchronous sampling and off-policy correction.
result Achieves 100,000 FPS on 3D control problems without sacrificing sample efficiency.
This paper develops a geometric framework for SHM using feature bundles and gauge theories.
problem Defining feature spaces in population-based SHM.
method Introduces feature bundles as sections of vector bundles over structure spaces, and uses Graph Neural Networks for feature assignment.
result Develops a mathematical framework for SHM that incorporates feature spaces and gauge theories.
Improved disentanglement of data factors using recursive training.
problem Current unsupervised disentanglement methods are inconsistent and fail to achieve levels of disentanglement seen in supervised approaches.
method Introduced PBT for VAEs, used UDR for heuristic scoring, and developed recursive rPU-VAE approach.
result Recursive training leads to robust disentanglement of data factors across multiple datasets.
Improves exploration in reinforcement learning with diverse population.
problem Lack of diversity in reinforcement learning agents leads to limited exploration.
method Optimizes a population of agents using volume of behavioral manifold and online learning techniques.
result Improves exploration without sacrificing performance.
Study improves engagement prediction in educational videos.
problem Addressing cold-start problem in educational recommenders.
method Introduced VLE dataset with content and engagement features, conducted experiments.
result VLE dataset leads to better engagement prediction models.
P3BO optimizes biological sequence design by combining multiple methods.
problem Variability in performance of black-box optimization methods for biological sequence design.
method Population-Based Black-Box Optimization (P3BO) that samples sequences from an ensemble of methods, weighting by past performance.
result P3BO outperforms individual methods, proposing higher quality and more diverse sequences.
Researchers developed a generic model to account for structural variability in SHM.
problem Variability in natural frequency due to operational and environmental conditions limits SHM technologies.
method An overlapping mixture of Gaussian processes (OMGP) was used to generate a generic representation of normal condition.
result The OMGP model provided a generic representation (form) to characterise the normal condition of structures.
Hybrid RL algorithms improve offline and online RL in linear MDPs.
problem Improving RL performance without single-policy concentrability.
method Developed computationally efficient algorithms for PAC and regret-minimizing RL in linear MDPs.
result Achieved sharper error or regret bounds for linear MDPs.
This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.
problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.
New method defends RL agents from poisoning attacks without MDP knowledge.
problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.
Reincarnating RL reuses prior work to accelerate RL progress.
problem Efficiency and accessibility in reinforcement learning for large-scale applications.
method Transfer of learned policies between RL agents or design iterations, focusing on value-based RL.
result Demonstrated gains in performance over tabula rasa RL on various tasks.
Paper shows RLHF can be solved similarly to standard RL.
problem Difficulty of RLHF compared to standard RL.
method Reduction to reward-based RL techniques.
result RLHF can be solved using existing algorithms for reward-based RL.
MaxEnt RL optimizes decision-making in uncertain environments.
problem MaxEnt RL optimizes decision-making in uncertain environments.
method Formal analysis of MaxEnt RL in POMDPs and adversarial reward games.
result MaxEnt RL optimally solves certain classes of control problems with uncertain reward functions.
RL tackles decision making in unknown environments, focusing on efficiency and efficacy.
problem Efficiency and efficacy in RL algorithms for sample-starved situations.
method Markov Decision Processes, model-based and value-based approaches, policy optimization.
result Enhanced understanding and improvements in sample and computational efficacies of RL algorithms.
Objectives: Most cancer data sources lack information on metastatic recurrence. Electronic medical records (EMRs) and population-based cancer registries contain complementary information on cancer treatment and outcomes, yet are rarely used synergistically. To enable detection of metastatic breast cancer (MBC), we appl…
Catalyst.RL accelerates RL research with efficient training.
problem Efficient reinforcement learning training in complex environments.
method Open-source PyTorch framework with distributed training and RL algorithms.
result Catalyst.RL achieved 2nd place in a computationally expensive RL challenge.
Study shows effectiveness of offline RL in online RL tasks.
problem Improving online RL efficiency using offline RL data.
method Formalized framework for incorporating offline RL as online RL subroutines, introducing techniques to enhance effectiveness.
result Effectiveness of the framework depends on task nature, techniques greatly enhance effectiveness, and existing methods are ineffective.
MOReL learns offline RL policies using pessimistic MDPs.
problem Offline RL's data efficiency and velocity.
method Two-step process: learn P-MDP and near-optimal policy in it.
result MOReL is minimax optimal and matches state-of-the-art results.
Developed a cost and revenue model for HEMS to estimate breakeven transport volumes under different reimbursement and labor cost assumptions.
problem Estimating breakeven transport volumes for HEMS under varying reimbursement and labor cost assumptions.
method Developed a two-part model: cost framework and actuarial revenue model using healthcare encounter data and payer reimbursement rates.
result Estimated breakeven transport volumes under different reimbursement and labor cost assumptions.
RL research overhypes potential but lacks deployable solutions.
problem Current RL research overhypes potential and lacks deployable solutions.
method Identifies and critiques current RL research practices.
result Current RL research direction is unlikely to lead to practical, economically viable solutions.
RL applied to finance tasks, highlighting challenges and future directions.
problem Decision-making tasks in finance using RL.
method Meta-analysis of RL applications, identifying challenges and proposing future directions.
result Challenges in RL performance and future research directions.
Reinforcement learning (RL) algorithms allow agents to learn skills and strategies to perform complex tasks without detailed instructions or expensive labelled training examples. That is, RL agents can learn, as we learn. Given the importance of learning in our intelligence, RL has been thought to be one of key compone…
Optimizes sampling in continuous domains by adjusting search distribution.
problem Improving sampling efficiency in continuous domains.
method Analyzes and refines the search distribution based on population size and dimension.
result Explicit values for reshaping the search distribution are provided.
A simple approach to offline RL without additional complexity.
problem Learning from a fixed dataset of actions with value estimation errors.
method Adding a behavior cloning term to the policy update of an online RL algorithm and normalizing the data.
result Matches the performance of state-of-the-art offline RL algorithms with minimal changes.
MVFST-RL tackles real-time network congestion control with RL.
problem Real-time network congestion control with RL in asynchronous environments.
method Asynchronous RL framework for delayed actions in QUIC.
result Scalable framework for congestion control in QUIC with improved state-of-the-art RL.
MiniHack simplifies creation of complex RL environments.
problem Limited availability of challenging RL benchmarks.
method Develops a sandbox framework for easy RL environment design.
result MiniHack enables rapid creation of diverse RL testbeds.