Kshitija Taywade, Brent Harrison, Adib Bagh
arXiv 1 Jan 2022 · cs.GT · publishedProceedings of the ... International Florida Artificial Intelligence Research Society Conference (2022) · 2 citations (OpenAlex)
arXiv:2201.01182 · PDF · DOI · OpenAlex · Extracted main text
We investigate the use of a multi-agent multi-armed bandit (MA-MAB) setting for modeling repeated Cournot oligopoly games, where the firms acting as agents choose from the set of arms representing production quantity (a discrete value). Agents interact with separate and independent bandit problems. In this formulation, each agent makes sequential choices among arms to maximize its own reward. Agents do not have any information about the environment; they can only see their own rewards after taking an action. However, the market demand is a stationary function of total industry output, and random entry or exit from the market is not allowed. Given these assumptions, we found that an $\epsilon$-greedy approach offers a more viable learning mechanism than other traditional MAB approaches, as it does not require any additional knowledge of the system to operate. We also propose two novel approaches that take advantage of the ordered action space: $\epsilon$-greedy+HL and $\epsilon$-greedy+EL. These new approaches help firms to focus on more profitable actions by eliminating less profitable choices and hence are designed to optimize the exploration. We use computer simulations to study the emergence of various equilibria in the outcomes and do the empirical analysis of joint cumulative regrets.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Ludo Waltman and Uzay Kaymak (2008) Q-learning agents in a Cournot oligopoly model | 0.874 | 7 | 2 | 100% |
| 2 | Tor Lattimore and Csaba Szepesvári (2020) Bandit algorithms | 0.737 | 3 | 2 | 100% |
| 3 | Wesley Cowan, Junya Honda, and Michael N Katehakis (2017) Normal bandits of unknown means and variances | 0.644 | 2 | 2 | 100% |
| 4 | Junya Honda and Akimichi Takemura (2014) Optimality of thompson sampling for gaussian bandits depends on priors | 0.644 | 2 | 2 | 100% |
| 5 | Nicolaas J Vriend (2000) An illustration of the essential difference between individual and social learning, and its consequences for computational analy… | 0.585 | 3 | 1 | 100% |
| 6 | Junyi Xu (2020) Reinforcement learning in a Cournot oligopoly model | 0.585 | 3 | 1 | 100% |
| 7 | Karsten Hansen, Kanishka Misra, and Mallesh Pai (2020) Algorithmic collusion: Supra-competitive prices via independent algorithms | 0.511 | 2 | 1 | 100% |
| 8 | Mridul Agarwal, Vaneet Aggarwal, and Kamyar Azizzadenesheli (2021) Multi-agent multi-armed bandits with limited communication | 0.405 | 1 | 1 | 100% |
| 9 | Animashree Anandkumar, Nithin Michael, Ao Kevin Tang, and Ananthram… (2011) Distributed algorithms for learning and cognitive medium access with logarithmic regret | 0.405 | 1 | 1 | 100% |
| 10 | Jasmina Arifovic and Michael K Maschek (2006) Revisiting individual evolutionary learning in the cobweb model–an illustration of the virtual spite-effect | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 46 scored citations.