A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Deep RL multi-task learning outperforms single-task learning on new tasks.
AR-A3C improves A3C's robustness to noisy environments.
Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experie…
We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network module at the foundation of its network architecture. To address the issue of sample…
Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based on Asynchronous Advantage Actor-Critic (A3C) algorithm where the total input dimensionality is halv…
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to p…
SLM Lab is a framework for reproducible RL research with modular algorithms.
Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreover, actions in such games typically involve particular sequential action orders, which also makes the…
After presenting Actor Critic Methods (ACM), we show ACM are control variate estimators. Using the projection theorem, we prove that the Q and Advantage Actor Critic (A2C) methods are optimal in the sense of the norm for the control variate estimators spanned by functions conditioned by the current state and acti…
Deep reinforcement learning has achieved great successes in recent years, but there are still open challenges, such as convergence to locally optimal policies and sample inefficiency. In this paper, we contribute a novel self-supervised auxiliary task, i.e., Terminal Prediction (TP), estimating temporal closeness to te…
Reinforcement learning improves trading performance on stock exchanges.
In 2015, Google's DeepMind announced an advancement in creating an autonomous agent based on deep reinforcement learning (DRL) that could beat a professional player in a series of 49 Atari games. However, the current manifestation of DRL is still immature, and has significant drawbacks. One of DRL's imperfections is it…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images is data inefficient. The agent must learn feature representation of complex stat…
In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optima…
LSAM optimizes deep learning training with improved efficiency.
This work tackles resource allocation in asynchronous and stochastic systems.
New Fourier transform method handles missing data and asynchronous observations.
This paper describes Plumbing for Optimization with Asynchronous Parallelism (POAP) and the Python Surrogate Optimization Toolbox (pySOT). POAP is an event-driven framework for building and combining asynchronous optimization strategies, designed for global optimization of expensive functions where concurrent function …
The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.
Deep Reinforcement Learning (DRL) algorithms are known to be data inefficient. One reason is that a DRL agent learns both the feature and the policy tabula rasa. Integrating prior knowledge into DRL algorithms is one way to improve learning efficiency since it helps to build helpful representations. In this work, we co…
Improved SAC with AWMP for better control tasks.
D2D-SPL uses discrete states and a classifier to train RL faster.
This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration. Our empirical results show that SIL sig…
TT-DAC-PS: A deterministic actor-critic approach for optimal trade execution
Smaller actor-critic models lead to performance degradation and overfitting, highlighting the critic's role in value underestimation.
New method combines value function decomposition and policy gradients for cooperative multi-agent reinforcement learning.
PEARL uses reinforcement learning to improve matrix preconditioners.
Paper proposes a new RL approach combining IL and RL methods to improve decision-making.
Efficient learning-based MPC for unknown nonlinear systems with state constraints.
WRAAC uses Wasserstein distance for robust reinforcement learning.
Ringmaster LMO accelerates training in distributed systems by asynchronously updating neural networks.
New algorithm reduces distributed optimization time with stochastic delays.
Paper provides convergence guarantees for off-policy NAC with finite sample complexity.
New algorithms solve nonconvex federated learning problems efficiently.
Capsule Networks improve autonomous navigation in sparse environments.
Pipelined Backpropagation trains large models without batches efficiently.
ADDA framework speeds up data augmentation in massive data settings.
Paper proposes a novel trading strategy combining clustering and reinforcement learning for multi-period portfolio management.
The analysis of the intraday dynamics of correlations among high-frequency returns is challenging due to the presence of asynchronous trading and market microstructure noise. Both effects may lead to significant data reduction and may severely underestimate correlations if traditional methods for low-frequency data are…
A new method for efficient optimization of expensive simulations on HPC.
Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to …
Topic models such as Latent Dirichlet Allocation (LDA) have been widely used in information retrieval for tasks ranging from smoothing and feedback methods to tools for exploratory search and discovery. However, classical methods for inferring topic models do not scale up to the massive size of today's publicly availab…
IDS improves reinforcement learning with contextual information.
MODULE solves LfO problem with high sample efficiency and stability.
The study uses AI to optimize trading in FX markets by considering size-dependent fees and risk-aversion.
Current imitation learning techniques are too restrictive because they require the agent and expert to share the same action space. However, oftentimes agents that act differently from the expert can solve the task just as good. For example, a person lifting a box can be imitated by a ceiling mounted robot or a desktop…
Any given classification problem can be modeled using multi-class or One-vs-All (OVA) architecture. An OVA system consists of as many OVA models as the number of classes, providing the advantage of asynchrony, where each OVA model can be re-trained independent of other models. This is particularly advantageous in setti…
We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization setup uses several threads, each applying individual gradient descents on a local variable. We propose a new way of sharing information bet…