Philipp Altmann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Philipp Altmann has a total of 67 co-authors. Here are the top co-authors by number of shared publications:
Claudia Linnhoff-Popien
LMU Munich, Munich, Germany
13 shared publicationsMaximilian Zorn
LMU Munich, Munich, Germany
11 shared publicationsThomas Gabor
LMU Munich, Munich, Germany
10 shared publicationsFabian Ritz
LMU Munich, Munich, Germany
9 shared publications- Michael Kölle
LMU Munich Munich Germany
9 shared publications Thomy Phan
7 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7003-7014
On Representation Smoothness for Robust Architecture Discovery of Variational Quantum Circuits
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7003-7014
Open AccessOn Representation Smoothness for Robust Architecture Discovery of Variational Quantum Circuits
- Open Access
- 30 March 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (4) , 329
Surrogate Fitness Metrics for Interpretable Reinforcement Learning
We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse reinforcement learning (RL) policy demonstrations. A surrogate fitness function guides the optimization by combining local diversity, behavioral certainty, and global population diversity. To assess demonstration quality, we apply a set of evaluation metrics, including the reward-based optimality gap, fidelity interquartile means (IQMs), fitness composition analysis, and trajectory visualizations. Hyperparameter sensitivity is also examined to better understand the dynamics of trajectory optimization. Our findings demonstrate that optimizing trajectory selection via surrogate fitness metrics significantly improves the interpretability of RL policies in both discrete and continuous environments. In gridworld domains, evaluations reveal significantly enhanced demonstration fidelities compared to random and ablated baselines. In continuous control, the proposed framework provides valuable insights, particularly for early-stage policies, whereas fidelity-based optimization is more effective for mature policies. By refining and systematically analyzing surrogate fitness functions, this study advances the interpretability of RL models. The proposed improvements provide deeper insights into RL decision-making, benefiting applications in safety-critical and explainability-focused domains.
- 30 March 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (4) , 329
Open AccessSurrogate Fitness Metrics for Interpretable Reinforcement Learning
We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse reinforcement learning (RL) policy demonstrations. A surrogate fitness function guides the optimization by combining local diversity, behavioral certainty, and global population diversity. To assess demonstration quality, we apply a set of evaluation metrics, including the reward-based optimality gap, fidelity interquartile means (IQMs), fitness composition analysis, and trajectory visualizations. Hyperparameter sensitivity is also examined to better understand the dynamics of trajectory optimization. Our findings demonstrate that optimizing trajectory selection via surrogate fitness metrics significantly improves the interpretability of RL policies in both discrete and continuous environments. In gridworld domains, evaluations reveal significantly enhanced demonstration fidelities compared to random and ablated baselines. In continuous control, the proposed framework provides valuable insights, particularly for early-stage policies, whereas fidelity-based optimization is more effective for mature policies. By refining and systematically analyzing surrogate fitness functions, this study advances the interpretability of RL models. The proposed improvements provide deeper insights into RL decision-making, benefiting applications in safety-critical and explainability-focused domains.
- Open Access
Quantum Generator Kernels
Quantum kernel methods offer significant theoretical benefits by rendering classically inseparable features separable in quantum space. Yet, the practical application of Quantum Machine Learning (QML), currently constrained by the limitations of Noisy Intermediate-Scale Quantum (NISQ) hardware, necessitates effective strategies to compress and embed large-scale real-world data like images into the constrained capacities of existing quantum devices or simulators. To this end, we propose Quantum Generator Kernels (QGKs), a generator-based approach to quantum kernels, comprising a set of Variational Generator Groups (VGGs) that merge universal generators into a parameterizable operator, ensuring scalable coverage of the available quantum space. Thereby, we address shortcomings of current leading strategies employing hybrid architectures, which might prevent exploiting quantum computing's full potential due to fixed intermediate embedding processes. To optimize the kernel alignment to the target domain, we train a weight vector to parameterize the projection of the VGGs in the current data context. Our empirical results demonstrate superior projection and classification capabilities of the QGK compared to state-of-the-art quantum and classical kernel approaches and show its potential to serve as a versatile framework for various QML applications.
Open AccessQuantum Generator Kernels
Quantum kernel methods offer significant theoretical benefits by rendering classically inseparable features separable in quantum space. Yet, the practical application of Quantum Machine Learning (QML), currently constrained by the limitations of Noisy Intermediate-Scale Quantum (NISQ) hardware, necessitates effective strategies to compress and embed large-scale real-world data like images into the constrained capacities of existing quantum devices or simulators. To this end, we propose Quantum Generator Kernels (QGKs), a generator-based approach to quantum kernels, comprising a set of Variational Generator Groups (VGGs) that merge universal generators into a parameterizable operator, ensuring scalable coverage of the available quantum space. Thereby, we address shortcomings of current leading strategies employing hybrid architectures, which might prevent exploiting quantum computing's full potential due to fixed intermediate embedding processes. To optimize the kernel alignment to the target domain, we train a weight vector to parameterize the projection of the VGGs in the current data context. Our empirical results demonstrate superior projection and classification capabilities of the QGK compared to state-of-the-art quantum and classical kernel approaches and show its potential to serve as a versatile framework for various QML applications.
- Open Access
Dynamic Incentivized Cooperation under Changing Rewards
Peer incentivization (PI) is a popular multi-agent reinforcement learning approach where all agents can reward or penalize each other to achieve cooperation in social dilemmas. Despite their potential for scalable cooperation, current PI methods heavily depend on fixed incentive values that need to be appropriately chosen with respect to the environmental rewards and thus are highly sensitive to their changes. Therefore, they fail to maintain cooperation under changing rewards in the environment, e.g., caused by modified specifications, varying supply and demand, or sensory flaws - even when the conditions for mutual cooperation remain the same. In this paper, we propose Dynamic Reward Incentives for Variable Exchange (DRIVE), an adaptive PI approach to cooperation in social dilemmas with changing rewards. DRIVE agents reciprocally exchange reward differences to incentivize mutual cooperation in a completely decentralized way. We show how DRIVE achieves mutual cooperation in the general Prisoner's Dilemma and empirically evaluate DRIVE in more complex sequential social dilemmas with changing rewards, demonstrating its ability to achieve and maintain cooperation, in contrast to current state-of-the-art PI methods.
Open AccessDynamic Incentivized Cooperation under Changing Rewards
Peer incentivization (PI) is a popular multi-agent reinforcement learning approach where all agents can reward or penalize each other to achieve cooperation in social dilemmas. Despite their potential for scalable cooperation, current PI methods heavily depend on fixed incentive values that need to be appropriately chosen with respect to the environmental rewards and thus are highly sensitive to their changes. Therefore, they fail to maintain cooperation under changing rewards in the environment, e.g., caused by modified specifications, varying supply and demand, or sensory flaws - even when the conditions for mutual cooperation remain the same. In this paper, we propose Dynamic Reward Incentives for Variable Exchange (DRIVE), an adaptive PI approach to cooperation in social dilemmas with changing rewards. DRIVE agents reciprocally exchange reward differences to incentivize mutual cooperation in a completely decentralized way. We show how DRIVE achieves mutual cooperation in the general Prisoner's Dilemma and empirically evaluate DRIVE in more complex sequential social dilemmas with changing rewards, demonstrating its ability to achieve and maintain cooperation, in contrast to current state-of-the-art PI methods.
- Open Access
- 8 December 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (35-36) , 29135-29136
Correction: Discriminative reward co-training
- 8 December 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (35-36) , 29135-29136
Open AccessCorrection: Discriminative reward co-training
- Open Access
- 16 September 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the International Conference on Automated Planning and Scheduling
- Vol. 35 (1) , 367-375
Quality Diversity for Variational Quantum Circuit Optimization
Optimizing the architecture of variational quantum circuits (VQCs) is crucial for advancing quantum computing (QC) towards practical applications. Current methods range from static ansatz design and evolutionary methods to machine learned VQC optimization, but are either slow, sample inefficient or require infeasible circuit depth to realize advantages. Quality diversity (QD) search methods combine diversity-driven optimization with user-specified features that offer insight into the optimization quality of circuit solution candidates. However, the choice of quality measures and the representational modeling of the circuits to allow for optimization with the current state-of-the-art QD methods like covariance matrix adaptation (CMA), is currently still an open problem. In this work we introduce a directly matrix-based circuit engineering, that can be readily optimized with QD-CMA methods and evaluate heuristic circuit quality properties like expressivity and gate-diversity as quality measures. We empirically show superior circuit optimization of our QD optimization w.r.t. speed and solution score against a set of robust benchmark algorithms from the literature on a selection of NP-hard combinatorial optimization problems.
- 16 September 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the International Conference on Automated Planning and Scheduling
- Vol. 35 (1) , 367-375
Open AccessQuality Diversity for Variational Quantum Circuit Optimization
Optimizing the architecture of variational quantum circuits (VQCs) is crucial for advancing quantum computing (QC) towards practical applications. Current methods range from static ansatz design and evolutionary methods to machine learned VQC optimization, but are either slow, sample inefficient or require infeasible circuit depth to realize advantages. Quality diversity (QD) search methods combine diversity-driven optimization with user-specified features that offer insight into the optimization quality of circuit solution candidates. However, the choice of quality measures and the representational modeling of the circuits to allow for optimization with the current state-of-the-art QD methods like covariance matrix adaptation (CMA), is currently still an open problem. In this work we introduce a directly matrix-based circuit engineering, that can be readily optimized with QD-CMA methods and evaluate heuristic circuit quality properties like expressivity and gate-diversity as quality measures. We empirically show superior circuit optimization of our QD optimization w.r.t. speed and solution score against a set of robust benchmark algorithms from the literature on a selection of NP-hard combinatorial optimization problems.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 934-942
Quantum Circuit Construction and Optimization through Hybrid Evolutionary Algorithms
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 934-942
Open AccessQuantum Circuit Construction and Optimization through Hybrid Evolutionary Algorithms
- Open Access
Surrogate Fitness Metrics for Interpretable Reinforcement Learning
We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse policy demonstrations. A joint surrogate fitness function guides the optimization by combining local diversity, behavioral certainty, and global population diversity. To assess demonstration quality, we apply a set of evaluation metrics, including the reward-based optimality gap, fidelity interquartile means (IQMs), fitness composition analysis, and trajectory visualizations. Hyperparameter sensitivity is also examined to better understand the dynamics of trajectory optimization. Our findings demonstrate that optimizing trajectory selection via surrogate fitness metrics significantly improves interpretability of RL policies in both discrete and continuous environments. In gridworld domains, evaluations reveal significantly enhanced demonstration fidelities compared to random and ablated baselines. In continuous control, the proposed framework offers valuable insights, particularly for early-stage policies, while fidelity-based optimization proves more effective for mature policies. By refining and systematically analyzing surrogate fitness functions, this study advances the interpretability of RL models. The proposed improvements provide deeper insights into RL decision-making, benefiting applications in safety-critical and explainability-focused domains.
Open AccessSurrogate Fitness Metrics for Interpretable Reinforcement Learning
We employ an evolutionary optimization framework that perturbs initial states to generate informative and diverse policy demonstrations. A joint surrogate fitness function guides the optimization by combining local diversity, behavioral certainty, and global population diversity. To assess demonstration quality, we apply a set of evaluation metrics, including the reward-based optimality gap, fidelity interquartile means (IQMs), fitness composition analysis, and trajectory visualizations. Hyperparameter sensitivity is also examined to better understand the dynamics of trajectory optimization. Our findings demonstrate that optimizing trajectory selection via surrogate fitness metrics significantly improves interpretability of RL policies in both discrete and continuous environments. In gridworld domains, evaluations reveal significantly enhanced demonstration fidelities compared to random and ablated baselines. In continuous control, the proposed framework offers valuable insights, particularly for early-stage policies, while fidelity-based optimization proves more effective for mature policies. By refining and systematically analyzing surrogate fitness functions, this study advances the interpretability of RL models. The proposed improvements provide deeper insights into RL decision-making, benefiting applications in safety-critical and explainability-focused domains.
- Open Access
- 11 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (23) , 18793-18809
Discriminative reward co-training
We propose discriminative reward co-training (DIRECT) as an extension to deep reinforcement learning algorithms. Building upon the concept of self-imitation learning (SIL), we introduce an imitation buffer to store beneficial trajectories generated by the policy, determined by their return. A discriminator network is trained concurrently to the policy to distinguish between trajectories generated by the current policy and beneficial trajectories generated by previous policies. The discriminator’s verdict is used to construct a reward signal for optimizing the policy. By interpolating prior experience, DIRECT is able to act as a reward surrogate, steering policy optimization toward more valuable regions of the reward landscape, thus, toward learning an optimal policy. In this article, we formally introduce the additional components, their intended purpose and parameterization, and define a unified training procedure. To reveal insights into the mechanics of the proposed architecture, we provide evaluations of the introduced hyperparameters. Further benchmark evaluations in various discrete and continuous control environments provide evidence that DIRECT is especially beneficial in environments possessing sparse rewards, hard exploration tasks, and shifting circumstances. Our results show that DIRECT outperforms state-of-the-art algorithms in those challenging scenarios by providing a surrogate reward to the policy and direct the optimization toward valuable areas.
- 11 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (23) , 18793-18809
Open AccessDiscriminative reward co-training
We propose discriminative reward co-training (DIRECT) as an extension to deep reinforcement learning algorithms. Building upon the concept of self-imitation learning (SIL), we introduce an imitation buffer to store beneficial trajectories generated by the policy, determined by their return. A discriminator network is trained concurrently to the policy to distinguish between trajectories generated by the current policy and beneficial trajectories generated by previous policies. The discriminator’s verdict is used to construct a reward signal for optimizing the policy. By interpolating prior experience, DIRECT is able to act as a reward surrogate, steering policy optimization toward more valuable regions of the reward landscape, thus, toward learning an optimal policy. In this article, we formally introduce the additional components, their intended purpose and parameterization, and define a unified training procedure. To reveal insights into the mechanics of the proposed architecture, we provide evaluations of the introduced hyperparameters. Further benchmark evaluations in various discrete and continuous control environments provide evidence that DIRECT is especially beneficial in environments possessing sparse rewards, hard exploration tasks, and shifting circumstances. Our results show that DIRECT outperforms state-of-the-art algorithms in those challenging scenarios by providing a surrogate reward to the policy and direct the optimization toward valuable areas.
- Open Access
Finding Strong Lottery Ticket Networks with Genetic Algorithms
According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the trained super-network. We present the first approach based on a genetic algorithm to find such strong lottery ticket sub-networks without training or otherwise computing any gradient. We show that, for smaller instances of binary classification tasks, our evolutionary approach even produces smaller and better-performing lottery ticket networks than the state-of-the-art approach using gradient information.
Open AccessFinding Strong Lottery Ticket Networks with Genetic Algorithms
According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the trained super-network. We present the first approach based on a genetic algorithm to find such strong lottery ticket sub-networks without training or otherwise computing any gradient. We show that, for smaller instances of binary classification tasks, our evolutionary approach even produces smaller and better-performing lottery ticket networks than the state-of-the-art approach using gradient information.