[PDF][PDF] PARL: A unified framework for policy alignment in reinforcement learning
We present a novel unified bilevel optimization-based framework, PARL, formulated to
address the recently highlighted critical issue of policy alignment in reinforcement learning …
address the recently highlighted critical issue of policy alignment in reinforcement learning …
Deep Reinforcement Learning: emerging trends in macroeconomics and future prospects
T Atashbar, RA Shi - 2022 - books.google.com
The application of Deep Reinforcement Learning (DRL) in economics has been an area of
active research in recent years. A number of recent works have shown how deep …
active research in recent years. A number of recent works have shown how deep …
A computational neuroscience perspective on subjective wellbeing within the active inference framework
R Smith, LR Varshney… - International …, 2022 - internationaljournalofwellbeing.org
Understanding and promoting subjective wellbeing (SWB) has been the topic of increasing
research, due in part to its potential contributions to health and productivity. To date, the …
research, due in part to its potential contributions to health and productivity. To date, the …
Aligning agent policy with externalities: Reward design via bilevel rl
In reinforcement learning (RL), a reward function is often assumed at the outset of a policy
optimization procedure. Learning in such a fixed reward paradigm in RL can neglect …
optimization procedure. Learning in such a fixed reward paradigm in RL can neglect …
Generative adversarial equilibrium solvers
We introduce the use of generative adversarial learning to compute equilibria in general
game-theoretic settings, specifically the generalized Nash equilibrium (GNE) in pseudo …
game-theoretic settings, specifically the generalized Nash equilibrium (GNE) in pseudo …
Adaptive model design for Markov decision process
In a Markov decision process (MDP), an agent interacts with the environment via
perceptions and actions. During this process, the agent aims to maximize its own gain …
perceptions and actions. During this process, the agent aims to maximize its own gain …
[PDF][PDF] Learning Solutions in Large Economic Networks using Deep Multi-Agent Reinforcement Learning.
Real-world economies can be modeled as a network with many heterogeneous and
strategic agents. In this setting, it is very challenging to find optimal mechanisms, eg, taxes …
strategic agents. In this setting, it is very challenging to find optimal mechanisms, eg, taxes …
[图书][B] AI and macroeconomic modeling: Deep reinforcement learning in an RBC model
T Atashbar, RA Shi - 2023 - books.google.com
This study seeks to construct a basic reinforcement learning-based AI-macroeconomic
simulator. We use a deep RL (DRL) approach (DDPG) in an RBC macroeconomic model …
simulator. We use a deep RL (DRL) approach (DDPG) in an RBC macroeconomic model …
ABIDES-Economist: Agent-Based Simulation of Economic Systems with Learning Agents
We introduce a multi-agent simulator for economic systems comprised of heterogeneous
Households, heterogeneous Firms, Central Bank and Government agents, that could be …
Households, heterogeneous Firms, Central Bank and Government agents, that could be …
Stochastic Bilevel Optimization with Lower-Level Contextual Markov Decision Processes
In various applications, the optimal policy in a strategic decision-making problem depends
both on the environmental configuration and exogenous events. For these settings, we …
both on the environmental configuration and exogenous events. For these settings, we …