.png){kind=icon}
.png){kind=icon}
Return
Reinforcement learning for continuous-time optimal execution: actor-critic algorithm and error analysis
.png){kind=icon}
PRE
AI
DOI：10.1007/s00780-026-00589-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose an actor-critic reinforcement learning (RL) algorithm for the optimal execution problem. We formulate a mean-quadratic variation objective regularised by Shannon entropy under the celebrated Almgren-Chriss model by allowing stochastic policies. We obtain in closed form the optimal value function and the optimal feedback policy, which is Gaussian. We then utilise these analytical results to parametrise our value function and control policy for RL. While standard actor-critic RL algorithms perform policy evaluation update and policy gradient update alternatingly, we introduce a recalibration step in addition to these two updates, which turns out to be critical for convergence. We develop a finite-time error analysis of our algorithm and show that it converges linearly under suitable conditions on the learning rates. We test our algorithm in three different types of market simulators built on the Almgren-Chriss model, historical data of order flow and a stochastic model of limit order books. Empirical results demonstrate the advantages of our algorithm over the classical statistical approach and a deep-learning-based RL algorithm.
Keywords:
Reinforcement learning
Optimal execution
Stochastic control
Actor-critic method
Finite-time error analysis
Convergence analysis
C45
C61
G19
Journal
F
IF:
1.4
Papers:
17
Citations:
0