AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion

Jakub Seredyński; Georgios Tsaousoglou

cs.AIAug 27, 2026

AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusion

Authors: Jakub Seredyński, Georgios Tsaousoglou

Organizations: Department of Applied Mathematics and Computer Science, Technical University of Denmark.

Abstract

As electricity market participants increasingly adopt learning-based agents for their bidding strategies, electricity markets are becoming algorithmic. Evidence from algorithmic markets in other domains shows that tacit collusion can arise purely through independent learning. Moreover, electricity markets are typically oligopolistic and feature repeated interaction among a small number of participants, making them structurally susceptible to non-competitive behavior. In the face of these observations, this paper investigates the hypothesis that tacit collusion may emerge in electricity markets where participants' actions are controlled by autonomous learning-based algorithms. We model strategic bidding as a repeated game with imperfect public monitoring, and model the participants' emergent behavior using multi-agent reinforcement learning. We propose a multi-dimensional set of criteria (going beyond profit comparisons against Nash equilibria) to assess whether the resulting behavior constitutes tacit collusion. Our experimental results showcase that such a danger is realistic for electricity markets: there are cases where agents do learn to sustain supra-competitive outcomes that are supportive of tacit collusion indicators, even though the agents were never instructed to collude.

Figures & tables

Generator	Bus	$P_{i}^{\max}$ [MW]	Marginal cost [EUR/MWh]
			Low	Medium	High
$G_{1}$	$N_{1}$	42	20	20	20
$G_{2}$	$N_{2}$	35	20	20	20
$G_{5}$	$N_{5}$	40	20	30	40
$G_{6}$	$N_{6}$	40	20	10	1

TABLE I: Strategic generators and marginal-cost cases.

Scenario	Demand	Cost diff.	Rationale
Grid – LowDemand – HighCostDiff	Low	High	Structured non-stationary regime with non-trivial deviation incentives.
Grid – LowDemand – MediumCostDiff	Low	Medium	Reference low-demand case with a more stationary learned profile.
Grid – MediumDemand – HighCostDiff	Medium	High	Higher-demand case that remains non-boundary and strategically informative.

TABLE II: Scenarios selected for behavioural validation.

Parameter	Value
Algorithm	Multi-agent TD3
Bid segments	12
Bidding parameter bounds	$[0,4000]$
Training length	100,000 market instances
Episodes / horizon	$50\times 2,000$
Evaluation window	Final 10,000 instances

TABLE III: Main MARL hyperparameters.

Panel of Figure 4 — Fig. 1: Price markups across the nine demand and marginal-cost heterogeneity combinations: (a) NoGrid scenarios without active transmission constraints and (b) Grid scenarios with active transmission constraints.

Fig. 2: Agents’ bidding actions during the Punishment of Deviation test for the three selected scenarios. The shaded region denotes the forced-deviation window, and the black line identifies the deviating agent.

Fig. 3: Agents’ rewards during the Punishment of Deviation test for the three selected scenarios. The shaded region denotes the forced-deviation window, and the black line identifies the deviating agent.

Fig. 4: Evolution of episode-average bidding slopes under the baseline MARL configuration and the shortsight ablation for the three selected scenarios. Solid lines denote the baseline agents and dashed lines the ablated agents.

Fig. 5: Agents’ bidding actions during the Punishment of Deviation test under the shortsight ablation for the three selected scenarios. The shaded region denotes the forced-deviation window, and the black line identifies the deviating agent.

Fig. 6: Agent reward trajectories under Iterative Best Response (IBR), initialized from the learned MARL outcomes. Iteration 0 corresponds to the MARL endpoint, while the horizontal dashed lines indicate the corresponding MARL reward levels.

Scenario	Punish.	Shortsight	IBR	Interpretation
Grid – LowDemand – HighCostDiff	Supportive	Supportive	Supportive	Collusion-consistent
Grid – LowDemand – MediumCostDiff	Supportive	Supportive	Supportive	Collusion-consistent
Grid – MediumDemand – HighCostDiff	Not supp.	Not supp.	Not supp.	Structural market power

TABLE IV: Summary of behavioural evidence for Tacit Collusion.

Algorithmic Collusion

Algorithmic collusion studies how software agents coordinate to weaken competition, how to detect such behavior, and how to prevent it.

See all 23 papers

Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets
Nov 12, 2025Tobias R. Rebholz, Maxwell Uphoff, Christian H. R. Bernges +1Algorithmic Collusion
Department of Psychology, University of Tübingen · Fuqua School of Business, Duke University · Department of Economics, University of Minnesota Twin Cities
Oblivious Learning and Collusive Pricing
Jun 3, 2026Yuhang Wu, Assaf ZeeviExploration-Exploitation Tradeoff Game Theory
Columbia Business School
Collusion with Competitive Marginals: Price-Level Audits Are Blind by Construction
Jul 29, 2026Xin Xu, Chengrui Wu, Jiayu Lu +3Algorithmic Auditing Automated Bidding
Carnegie Mellon University · Zhejiang University

Nov 12, 2025J/K move · Enter open · S save

Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets

Tobias R. Rebholz, Maxwell Uphoff, Christian H. R. Bernges, Florian Scholten

Department of Psychology, University of Tübingen · Fuqua School of Business, Duke University · Department of Economics, University of Minnesota Twin Cities

Algorithmic Collusion

Open paper AskPDF arXiv

As algorithms increasingly mediate competitive decision-making, their influence extends beyond individual outcomes to shaping strategic market dynamics. In our experiment, we examined how algorithmic advice affects human behavior in a classic economic game with a unique, non-collusive, and analytically traceable equilibrium. Participants (N = 129) played a Cournot quantity competition with equilibrium-aligned or strategically biased algorithmic recommendations. While individualized equilibrium advice supported stable convergence, collusively downward-biased advice led to sustained underproduction and supracompetitive profits - hallmarks of tacit collusion. Participants' quantities converged faster and more consistently toward individualized than collective equilibrium advice, potentially due to an objective quality advantage or greater perceived ownership of the former. These findings demonstrate that algorithmic advice can function as a strategic signal, shaping coordination even without explicit communication. The results echo real-world concerns about algorithmic collusion and underscore the need for careful design and oversight of algorithmic decision-support systems in competitive environments.

Abstract

Algorithmic Collusion

Explore similar work

Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets

Oblivious Learning and Collusive Pricing

Collusion with Competitive Marginals: Price-Level Audits Are Blind by Construction