Loss of plasticity in continual deep reinforcement learning
In this paper, we characterize the behavior of canonical value-based deep reinforcement
learning (RL) approaches under varying degrees of non-stationarity. In particular, we …
learning (RL) approaches under varying degrees of non-stationarity. In particular, we …
[HTML][HTML] An analysis of multi-agent reinforcement learning for decentralized inventory control systems
M Mousa, D van de Berg, N Kotecha… - Computers & Chemical …, 2024 - Elsevier
Most solutions to the inventory management problem assume a centralization of information
that is incompatible with organizational constraints in supply chain networks. The problem …
that is incompatible with organizational constraints in supply chain networks. The problem …
Policy optimization for continuous reinforcement learning
We study reinforcement learning (RL) in the setting of continuous time and space, for an
infinite horizon with a discounted objective and the underlying dynamics driven by a …
infinite horizon with a discounted objective and the underlying dynamics driven by a …
Hindsight learning for mdps with exogenous inputs
Many resource management problems require sequential decision-making under
uncertainty, where the only uncertainty affecting the decision outcomes are exogenous …
uncertainty, where the only uncertainty affecting the decision outcomes are exogenous …
Algorithmic and human collusion
T Werner - Available at SSRN 3960738, 2024 - papers.ssrn.com
I study self-learning pricing algorithms and show that they are collusive in market
simulations. To derive a counterfactual that resembles traditional tacit collusion, I conduct …
simulations. To derive a counterfactual that resembles traditional tacit collusion, I conduct …
Deep reinforcement learning for continuous wood drying production line control
Continuous high-frequency wood drying, when integrated with a traditional wood finishing
line, allows correcting moisture content one piece of lumber at a time in order to improve its …
line, allows correcting moisture content one piece of lumber at a time in order to improve its …
Model-based reinforcement learning with scalable composite policy gradient estimators
In model-based reinforcement learning (MBRL), policy gradients can be estimated either by
derivative-free RL methods, such as likelihood ratio gradients (LR), or by backpropagating …
derivative-free RL methods, such as likelihood ratio gradients (LR), or by backpropagating …
Neural inventory control in networks via hindsight differentiable policy optimization
Inventory management offers unique opportunities for reliably evaluating and applying deep
reinforcement learning (DRL). Rather than evaluate DRL algorithms by comparing against …
reinforcement learning (DRL). Rather than evaluate DRL algorithms by comparing against …
Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insights
Y Wang, LK Sambasivan, M Fu, P Mehrotra - arXiv preprint arXiv …, 2024 - arxiv.org
Generative AI applications, such as ChatGPT or DALL-E, have shown the world their
impressive capabilities in generating human-like text or image. Diving deeper, the science …
impressive capabilities in generating human-like text or image. Diving deeper, the science …