Learning to trade via direct reinforcement

By John E. Moody, Matthew Saffell. IEEE Trans. Neural Networks, 2001

560 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/1a4999c918c6206cd9804c48f7dce1bac6ec5b4a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Management Science and Operations Research

Citations in the corpus

Deep reinforcement learning for automated stock trading: an ensemble strategy (2020, unknown): “[24].”
Stock Trading Using RSPOP: A Novel Rough Set-Based Neuro-Fuzzy Approach (2006, background): “Moody et al. [23], [25] used recurrent reinforcement learning without forecasting to train a trading system to trade using past prices of S&P500 stock index while accounting for the effects of transaction costs (please refer to [26] for details on reinforcement learning).”
A Novel Fuzzy Associative Memory Architecture for Stock Market Prediction and Trading (2011, background): “88 data” for several highly volatile and consumer stocks (Saad et al., 1998; Moody & Saffell, 2001; Chen et al., 2003).”
Agent Inspired Trading Using Recurrent Reinforcement Learning and LSTM Neural Networks (2017, background): “Moody et al.[7] shown that how differential forms of the Sharpe Ratio and Downside Deviation Ratio can be formulated to enable efficient on-line learning with recurrent reinforcement learning, Lu[8] had shown using Linear Matrix Inequilities can beat the risk free rate, and Deng et al.”
Automated trading with boosting and expert weighting (2010, unknown): “In this respect, an indicator to evaluate the performance of an algorithm used by traders is the maximum drawdown (Di,t) [25, 54].”
Deep Direct Reinforcement Learning for Financial Signal Representation and Trading (2017, methodology): “The first competitor is the DRL system [17].”
Learning the Variance of the Reward-To-Go (2016, methodology): “More recently, Morimura et al. (2010) proposed TD learning rules for a parametric distribution of the return, albeit without function approximation nor formal guarantees.”
A Hybrid Reinforcement Learning Approach to Autonomic Resource Allocation (2006, background): “In addition to firm theoretical support in the MDP (Markov Decision Process) case, there have also been many notable successful applications of RL over the last decade in real-world problems ranging from helicopter control to financial markets trading to worldchampionship game playing [7], [8], [9].”
A Multi-objective Deep Reinforcement Learning Approach for Stock Index Future’s Intraday Trading (2017, background): “IF IH IC SR AP TT SR AP TT SR AP TT B&H -0.023 -0.51 - -0.0028 -0.43 - -0.16 -10.03 - RRL 0.73 1.02 6 -0.0097 -1.09 46 0.083 4.44 64 MODRL 0.12 2.66 62 0.11 1.8 80 0.11 8.30 91 Table I PERFORMANCES OF DIFFERENT TRADING SYSTEMS ON DIFFERENT CONTRACTS [5] J. Moody and M. Saffell, “Learning to trade vi”
Solving Deep Memory POMDPs with Recurrent Policy Gradients (2007, background): “see [1–5]) as they can deal with continuous states and actions.”
Recurrent policy gradients (2010, unknown): “, [3, 7, 10–14] for an overview.”
On the use of hybrid reinforcement learning for autonomic resource allocation (2007, background): “In addition to firm theoretical support in Markovian environments, RL practitioners over the last decade have also achieved notable practical success in many real-world problems ranging from helicopter control to financial markets trading to world-championship game playing [13–15], even though such ”
Financial volatility trading using a self-organising neural-fuzzy semantic network and option straddle-based approach (2010, methodology): “…ﬁnancial variables (Noh et al., 1994; Refenes, Burgess, & Bentz, 1997), equity returns (Apte & Hong, 1994; Kuan & Liu, 1995) and stock market indices (Chen, Leung, & Daouk, 2003; Yang & Yang, 2003), as well as the optimization of portfolio composition and trading strategy (Moody & Saffell, 2001).”
Cloning Strategies from Trading Records using Agent-based Reinforcement Learning Algorithm (2018, methodology): “[2] presented methods for optimizing asset allocations and trading systems called direct reinforcement based on recurrent reinforcement (RRL) for finding investment policies.”
State-Dependent Exploration for Policy Gradient Methods (2008, background): “in robotics [7], financial data prediction [8] or network routing [9].”