paper-with-me

홈 › Papers

Policy Space Identification in Configurable Environments

2019-09-09 · Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli

We study the problem of identifying the policy space of a learning agent, having access to a set of demonstrations generated by its optimal policy. We introduce an approach based on statistical testing to identify the set of policy parameters the agent can control, within a larger parametric policy space. After presenting two identification rules (combinatorial and simplified), applicable under different assumptions on the policy space, we provide a probabilistic analysis of the simplified one in the case of linear policies belonging to the exponential family. To improve the performance of our identification rules, we frame the problem in the recently introduced framework of the Configurable Markov Decision Processes, exploiting the opportunity of configuring the environment to induce the agent revealing which parameters it can control. Finally, we provide an empirical evaluation, on both discrete and continuous domains, to prove the effectiveness of our identification rules.

📄 PDF Abstract BibTeX arXiv:1909.03984

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Synthetic Monitoring Environments for Reinforcement Learning

2026-03-06 · Leonard Pleiss, Carolin Schmidt, Maximilian Schiffer arxiv

Reinforcement Learning (RL) lacks benchmarks that enable precise, white-box diagnostics of agent behavior. Current environments often entangle complexity factors and lack ground-truth optimality metrics, making it diffic…

Reinforcement LearningContinuous Control

Transfer Learning for Performance Modeling of Configurable Systems: A Causal Analysis

2019-02-26 · Mohammad Ali Javidian, Pooyan Jamshidi, Marco Valtorta

Modern systems (e.g., deep neural networks, big data analytics, and compilers) are highly configurable, which means they expose different performance behavior under different configurations. The fundamental challenge is …

Transfer Learning

Unicorn: Reasoning about Configurable System Performance through the lens of Causality

2022-01-20 · Md Shahriar Iqbal, Rahul Krishna, Mohammad Ali Javidian, Baishakhi Ray 외

Modern computer systems are highly configurable, with the total variability space sometimes larger than the number of atoms in the universe. Understanding and reasoning about the performance behavior of highly configurab…

BIG-bench Machine LearningCausal InferenceManagement

Near-optimal Policy Identification in Active Reinforcement Learning

2022-12-19 · Xiang Li, Viraj Mehta, Johannes Kirschner, Ian Char 외

Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces. In cases where the transition dynamics can be readily …

Bayesian Optimizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

A Comparison of Policy Search in Joint Space and Cartesian Space for Refinement of Skills

2019-04-14 · Alexander Fabisch

Imitation learning is a way to teach robots skills that are demonstrated by humans. Transfering skills between these different kinematic structures seems to be straightforward in Cartesian space. Because of the correspon…

Imitation Learning