Sidney N Givigi
Biographic Data
| ID | 10054972 |
|---|---|
| NAME | Sidney N Givigi |
| GIVEN NAMES | Sidney N |
| FAMILY NAME | Givigi |
| SIGNATURE | GIVIGI S N |
| AFFILIATIONS | Queen's University |
| ORCID | 0000-0002-3829-3545 |
| VERIFIED | Yes |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 2 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2024 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 0 |
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 structur…
Causal Reinforcement Learning in Iterated Prisoner’s Dilemma
The iterated prisoner’s dilemma (IPD) is an archetypal paradigm to model cooperation and has guided studies on social dilemmas. In this work, we develop a causal reinforcement learning (CRL) strategy in a PD game. An agent is designed to have an explicit causal representation of other agents playing strategies from the Axelrod tournament. The collection of policies is assembled in an ensemble RL to choose the best strategy. The agent is then test…
No prominent works on this page.
Causal Reinforcement Learning in Iterated Prisoner’s Dilemma
The iterated prisoner’s dilemma (IPD) is an archetypal paradigm to model cooperation and has guided studies on social dilemmas. In this work, we develop a causal reinforcement learning (CRL) strategy in a PD game. An agent is designed to have an explicit causal representation of other agents playing strategies from the Axelrod tournament. The collection of policies is assembled in an ensemble RL to choose the best strategy. The agent is then test…
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 structur…
Artificial Intelligence (2 works) · Computer Science (2 works) · Experimental Behavioral Economics Studies (2 works) · Machine learning (2 works) · Reinforcement learning (2 works) · Dilemma (1 works) · Evolutionary Game Theory and Cooperation (1 works) · Fuzzy logic (1 works) · Game theory (1 works) · Game Theory and Applications (1 works)