Improved A2C method with lower variance.
problem Reducing variance in deep policy gradient methods.
method Using control variate theory, derived a new A2C formulation with lower variance.
result New A2C method has lower variance and improved performance.
Multi-simulator training has contributed to the recent success of Deep Reinforcement Learning by stabilizing learning and allowing for higher training throughputs. We propose Gossip-based Actor-Learner Architectures (GALA) where several actor-learners (such as A2C agents) are organized in a peer-to-peer communication t…
Reinforcement learning (RL) is a promising data-driven approach for adaptive traffic signal control (ATSC) in complex urban traffic networks, and deep neural networks further enhance its learning power. However, centralized RL is infeasible for large-scale ATSC due to the extremely high dimension of the joint action sp…
The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.
problem Scalarization issues in A2C RL algorithms leading to gradient overlap and uncontrolled noise.
method Proposes techniques to avoid gradient overlap and noise in A2C RL algorithms.
result Pilot experiments show the proposed method speeds up training in A2C RL algorithms.
Deep RL fails on deceptive games, revealing algorithm weaknesses.
problem Characterizing and understanding failures of deep reinforcement learning.
method Testing A2C on four deceptive games using a game framework.
result Deep RL fails in specific ways that differ from planning-based agents.
This paper analyzes DRL strategies in finance, revealing unique trading patterns and performance differences.
problem Limited research on DRL behavior in finance applications.
method Analysis of trading behaviors and purchase diversity of DRL algorithms (A2C, PPO, SAC, DDPG, TD3).
result DRL algorithms exhibit distinct trading patterns and performance differences, with A2C outperforming others in terms of cumulative rewards.
KG-A2C agent learns natural language IF games by reasoning and constraining action spaces.
problem Challenges of natural language understanding, partial observability, and combinatorially large action spaces in IF games.
method Builds a dynamic knowledge graph while exploring, constraining actions using templates.
result Outperforms current IF agents across various games with larger action spaces.
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…
Deep RL algorithms struggle with noisy rewards in portfolio optimisation.
problem Evaluating deep reinforcement learning for portfolio optimisation with market impact.
method Simulated data with geometric Brownian motion and market impact model; Kelly criterion as upper bound; PPO and A2C with GAE; clipping; hidden Markov model for regime changes.
result PPO and A2C with GAE perform better with noisy rewards; PPO with HMM learns different policies for regime changes.
QTMRL uses RL with multi-indicators to improve trading adaptability.
problem Traditional trading models fail in volatile markets due to rigid assumptions.
method Combines multi-indicators with RL for adaptive portfolio management.
result QTMRL outperforms baselines in profitability and risk control.
In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC. We perform a range of empirical analysis on various aspects of the algorithm, such as sample complexity, training speed, and sensitivity to batch size and training epochs…
We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process. To address this issue, we propose a new method, …
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…
DRL improves ESG financial portfolio management by regulating returns based on ESG scores.
problem Improving ESG financial portfolio management through market regulation.
method Used Advantage Actor-Critic (A2C) agent and adapted OpenAI Gym environments for comparative analysis.
result DRL agent outperforms standard market conditions in ESG-regulated market.
Study explores reinforcement learning in a complex game environment, analyzing rule inference and policy learning.
problem Learning optimal policies in environments with hidden rules.
method Investigated using the Game Of Hidden Rules (GOHR) environment, employing Feature-Centric and Object-Centric state representations with a Transformer-based A2C algorithm.
result Transformer-based A2C models outperform traditional methods in GOHR, demonstrating the effectiveness of representation strategies.
Deep learning improves portfolio management by optimizing asset weights.
problem Traditional portfolio managers are outperformed by deep learning models in trading.
method Proposes a deep reinforcement learning portfolio manager that allocates weights to assets.
result The proposed portfolio manager outperforms conventional managers in risk-adjusted returns.
Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process (MDP) and trained through Reinforcement Learning (RL). Several RL models have been…
Study uses reinforcement learning to optimize portfolios under recursive utility.
problem Improving portfolio allocation using risk-sensitive objectives.
method Approximated certainty equivalent via Monte Carlo, trained actor-critic algorithms (PPO, A2C).
result Recursive-utility agent outperforms discounted baseline in Sharpe ratio, max drawdown, and cumulative return.
CuLE accelerates reinforcement learning on GPUs.
problem Limited CPU-GPU communication bandwidth in Atari Learning Environment.
method CUDA port of ALE, leveraging GPU parallelization and direct frame rendering.
result Up to 155M frames per hour on a single GPU, accelerating reinforcement learning.
Combines Hebbian and DQN for better POMDP problem solving.
problem Difficult POMDP problems with TD errors.
method Modulated Hebbian plus Q network architecture (MOHQA) integrating Hebbian and DQN.
result Improved DQN performance and outperformed other algorithms on some POMDPs.
This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space. We first present an approach for the disentanglement of vulnerabilities caused by representation learning of DRL agents from those that stem from the sensitivity of the DR…
Visual attention serves as a means of feature selection mechanism in the perceptual system. Motivated by Broadbent's leaky filter model of selective attention, we evaluate how such mechanism could be implemented and affect the learning process of deep reinforcement learning. We visualize and analyze the feature maps of…
In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design problem, or close variants thereof, have been proposed in the literature. In this…
Deep RL ensemble strategy outperforms individual algorithms in stock trading.
problem Designing profitable stock trading strategies in a complex market.
method Ensemble of three deep reinforcement learning algorithms (PPO, A2C, DDPG) for stock trading.
result Deep ensemble strategy outperforms individual algorithms and traditional min-variance portfolio.
TT-DAC-PS: A deterministic actor-critic approach for optimal trade execution
problem Optimal execution of large stock sell programs
method Twin-Target Deterministic Actor-Critic with Policy Smoothing
result Reduces mean implementation shortfall percentage
Deep RL improves robot navigation in images.
problem Applying deep RL to visual navigation in realistic environments.
method Extended A2C algorithm with auxiliary tasks for segmentation, depth prediction, and target prediction.
result Method outperforms state-of-the-art visual navigation methods.
Paper applies RL to optimize inventory management across multiple products and nodes.
problem Optimizing inventory management for a large number of products with shared capacity in a multi-node supply chain.
method Novel multi-agent hierarchical reinforcement learning framework with A2C algorithm and quantised action spaces.
result The approach optimizes for maximizing product sales and minimizing wastage of perishable products.
Paper optimizes GEMM for deep learning models, improving performance.
problem Limited GEMM optimization in deep learning frameworks restricts performance on different hardware.
method Proposes two novel algorithms: Greedy Best First Search (G-BFS) and Neighborhood Actor Advantage Critic (N-A2C) based on TVM framework.
result Significant performance improvements in GEMM computation time, achieving up to 40% savings.
Paper introduces MVS to detect non-Markovian observations in reinforcement learning.
problem Real-world sensors violate Markov property, leading to suboptimal reinforcement learning performance.
method Uses prediction-based Markov Violation Score (MVS) combining random forest and ridge regression.
result MVS detects non-Markovian structure in observation trajectories, quantifying its impact.
Paper combines RL with classifiers to improve financial trading strategies.
problem Enhancing risk-return trade-offs in trading strategies.
method Combining Reinforcement Learning (RL) models with traditional classifiers like SVM, Decision Trees, and Logistic Regression.
result Ensemble methods often outperform base models in risk-adjusted returns.
A novel neural network training method reduces gradient variance for faster and better reinforcement learning.
problem Improving convergence and generalization in deep reinforcement learning.
method Gradient Monitoring (GM) approach to dynamically adjust the learning process based on feedback.
result The proposed methods, especially AM-WGM, significantly enhance model performance and generalization.
Unified distributed SGD improves non-convex optimization for large datasets.
problem Bottleneck in scaling SGD for non-convex functions and large datasets.
method Distributed and parallel implementation of SGD (DPSGD) combining asynchronous distribution and lock-free parallelism.
result DPSGD achieves better convergence rate and speed-up with more cores and workers.
User releases data to service provider while balancing privacy and utility.
problem Balancing user privacy and service utility in data release.
method Formulated as a Markov decision process (MDP) and solved using deep reinforcement learning (RL).
result Achieved a trade-off between revealing useful information and protecting sensitive data.
FinRL simplifies deep RL for stock trading, making it accessible to beginners.
problem Lack of accessible tools for beginners in deep RL for stock trading.
method Developed a DRL library with reproducible tutorials and backtesting.
result FinRL streamlines development and comparison of trading strategies.
Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has proven successful in environments where transition models are known a priori. However, in complex environments where transition models need t…
Air traffic control is a real-time safety-critical decision making process in highly dynamic and stochastic environments. In today's aviation practice, a human air traffic controller monitors and directs many aircraft flying through its designated airspace sector. With the fast growing air traffic complexity in traditi…
RL agents outperform baselines in asset allocation.
problem Optimizing asset allocation using reinforcement learning.
method Model-free deep RL agents trained on real-world stock prices.
result RL agents significantly outperformed random and uniform allocation.
This work addresses privacy issues in IoT data sharing by balancing information disclosure and user privacy.
problem Balancing privacy and utility in time-series data sharing from IoT devices.
method Formulated as POMDPs, solved using A2C DRL, evaluated with synthetic and real data.
result Proposed policies achieve a good balance between privacy and utility.
Examines algorithmic modeling across three cultures.
problem Tackles algorithmic modeling in different cultural contexts.
method Uses parametric regressions, interpretable algorithms, and complex algorithms.
result Extension of Leo Breiman's thesis to include cultural differences.
Playing repeated matrix games (RMG) while maximizing the cumulative returns is a basic method to evaluate multi-agent learning (MAL) algorithms. Previous work has shown that UCB, M3, S or Exp3 algorithms have good behaviours on average in RMG. Besides, hedging algorithms have been shown to be effective on predi…
Meta-algorithm selection aims to choose the best algorithm selector for a given problem instance.
problem Selecting the best algorithm selector for a specific problem instance.
method Apply algorithm selection to the selection of other algorithms (meta-algorithm selection).
result Meta-algorithm selection can be beneficial in some cases but faces challenges in solving the meta-level problem.
Proposes CLRS benchmark to evaluate algorithmic reasoning.
problem Difficulty in transferring results across publications due to targeted algorithmic data.
method Develops a comprehensive benchmark covering various algorithmic tasks.
result Demonstrates performance of algorithmic reasoning baselines on the CLRS benchmark.
Combines multiple bandit algorithms to create a nearly optimal single algorithm.
problem Designing a single bandit algorithm that performs nearly as well as the best individual algorithm in a stochastic environment.
method Develops two general corralling algorithms that achieve favorable regret guarantees.
result The regret of the corralling algorithms is no worse than the best individual algorithm's performance.
We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known rando…
The exchange algorithm is studied for its convergence and asymptotic variance.
problem Theoretical limitations of the exchange algorithm in sampling from doubly-intractable distributions.
method Theoretical analysis of the exchange algorithm's convergence speed and asymptotic variance.
result The exchange algorithm converges at a geometric rate and satisfies a Central Limit Theorem.
Bayesian networks (BN) are used in a big range of applications but they have one issue concerning parameter learning. In real application, training data are always incomplete or some nodes are hidden. To deal with this problem many learning parameter algorithms are suggested foreground EM, Gibbs sampling and RBE algori…
No algorithm outperforms uniform sampling in A/B testing.
problem Identifying the best arm in A/B testing with fixed budget.
method Introducing consistent and stable algorithms, deriving lower bounds, and proving optimality of uniform sampling.
result No algorithm performs better than uniform sampling in A/B testing.
Improves algorithm selection for thousands of candidates using dyadic features.
problem Selecting the best algorithm from a large set of candidates for specific problems.
method Proposes extreme algorithm selection (XAS) with dyadic feature representation.
result Improves significantly over current state of the art in various metrics.