Rachel M. Haighton
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Rachel M. Haighton has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Howard M. Schwartz
Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada
2 shared publications - Sidney Nascimento Givigi
Queen’s University, Canada
2 shared publications - Amirhossein Asgharnia
Carleton Univ, Dept Syst & Comp Engn, 1125 Colonel By Dr, Ottawa, ON K1S 5B6, Canada
1 shared publication
Latest Publications
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (1) , 348-361
Altruism in Fuzzy Reinforcement Learning
We propose using a genetic algorithm to select hyperparameters in multiagent reinforcement learning (MARL) settings. In particular, we look at this in the context of cooperation and altruism. We show through the use of three continuous space games, that certain algorithmic hyperparameters are better suited to allow to agents learn altruistic behaviors. The agents learn using fuzzy actor critic learning algorithms in either a hierarchical structure or a single actor critic policy. The genetic algorithm selects the discount factors, the reward weights, and the standard deviation of noise applied to actor during learning. The genetic algorithm uses a fitness function based on the ratio of successful tests the group of agents can pass after training. This automated selection of these specific hyperparameters show that they are important for cooperation and also not trivial to select.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (1) , 348-361
Altruism in Fuzzy Reinforcement Learning
We propose using a genetic algorithm to select hyperparameters in multiagent reinforcement learning (MARL) settings. In particular, we look at this in the context of cooperation and altruism. We show through the use of three continuous space games, that certain algorithmic hyperparameters are better suited to allow to agents learn altruistic behaviors. The agents learn using fuzzy actor critic learning algorithms in either a hierarchical structure or a single actor critic policy. The genetic algorithm selects the discount factors, the reward weights, and the standard deviation of noise applied to actor during learning. The genetic algorithm uses a fitness function based on the ratio of successful tests the group of agents can pass after training. This automated selection of these specific hyperparameters show that they are important for cooperation and also not trivial to select.
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1421-1428
Hierarchical Reinforcement Learning for Non-Stationary Environments
What indications are there when the environment changes and the learned policy is no longer optimal? Is it possible to predict when a non-stationary environment changes in some way? In this paper we propose a method that helps agents know when to retrain their policies via reinforcement learning. The agents detect changes based on the temporal difference. A hierarchical learning model is used to aid in these non- stationary environments. The hierarchical learning model has two levels, the higher-level policy, which we call the learning switch, and the lower-level policy, which tells the agents their suitable action to play the game. The higher-level policy determines when reinforcement learning should be turned on or off based on the temporal differences calculated within a game or episode. Two multi-agent differential games are used as examples. The first two examples tackle the problem in cooperative games, while the last example addresses the competitive game. The results show that the agents can maintain suitable performance by switching on the learning process for a few iterations after environment changes occurs. In this paper we consider the change in environment to be long term occurrence within the dynamics of games; for example the mass of an agent may become heavier.
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1421-1428
Hierarchical Reinforcement Learning for Non-Stationary Environments
What indications are there when the environment changes and the learned policy is no longer optimal? Is it possible to predict when a non-stationary environment changes in some way? In this paper we propose a method that helps agents know when to retrain their policies via reinforcement learning. The agents detect changes based on the temporal difference. A hierarchical learning model is used to aid in these non- stationary environments. The hierarchical learning model has two levels, the higher-level policy, which we call the learning switch, and the lower-level policy, which tells the agents their suitable action to play the game. The higher-level policy determines when reinforcement learning should be turned on or off based on the temporal differences calculated within a game or episode. Two multi-agent differential games are used as examples. The first two examples tackle the problem in cooperative games, while the last example addresses the competitive game. The results show that the agents can maintain suitable performance by switching on the learning process for a few iterations after environment changes occurs. In this paper we consider the change in environment to be long term occurrence within the dynamics of games; for example the mass of an agent may become heavier.