Strictly batch imitation learning by energy-based distribution matching

D Jarrett, I Bica… - Advances in Neural …, 2020‏ - proceedings.neurips.cc
Consider learning a policy purely on the basis of demonstrated behavior---that is, with no
access to reinforcement signals, no knowledge of transition dynamics, and no further …

Hybrid residual multiexpert reinforcement learning for spatial scheduling of high-density parking lots

J Hou, G Chen, Z Li, W He, S Gu… - IEEE transactions on …, 2023‏ - ieeexplore.ieee.org
Industries, such as manufacturing, are accelerating their embrace of the metaverse to
achieve higher productivity, especially in complex industrial scheduling. In view of the …

Inverse decision modeling: Learning interpretable representations of behavior

D Jarrett, A Hüyük… - … Conference on Machine …, 2021‏ - proceedings.mlr.press
Decision analysis deals with modeling and enhancing decision processes. A principal
challenge in improving behavior is in obtaining a transparent* description* of existing …

Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems

A Likmeta, AM Metelli, G Ramponi, A Tirinzoni… - Machine Learning, 2021‏ - Springer
In real-world applications, inferring the intentions of expert agents (eg, human operators)
can be fundamental to understand how possibly conflicting objectives are managed, hel** …

Truly batch model-free inverse reinforcement learning about multiple intentions

G Ramponi, A Likmeta, AM Metelli… - International …, 2020‏ - proceedings.mlr.press
Abstract We consider Inverse Reinforcement Learning (IRL) about multiple intentions,\ie the
problem of estimating the unknown reward functions optimized by a group of experts that …

Robust learning from demonstrations with mixed qualities using leveraged gaussian processes

S Choi, K Lee, S Oh - IEEE Transactions on Robotics, 2019‏ - ieeexplore.ieee.org
In this paper, we focus on the problem of learning from demonstration (LfD) where
demonstrations with different proficiencies are provided without labeling. To this end, we …

Inferring the strategy of offensive and defensive play in soccer with inverse reinforcement learning

P Rahimian, L Toka - International Workshop on Machine Learning and …, 2021‏ - Springer
Analyzing and understanding strategies applied by top soccer teams has always been in the
focus of coaches, scouts, players, and other sports professionals. Although the game …

Policy space identification in configurable environments

AM Metelli, G Manneschi, M Restelli - Machine Learning, 2022‏ - Springer
We study the problem of identifying the policy space available to an agent in a learning
process, having access to a set of demonstrations generated by the agent playing the …

[ספר][B] Exploiting environment configurability in reinforcement learning

AM Metelli - 2022‏ - books.google.com
In recent decades, Reinforcement Learning (RL) has emerged as an effective approach to
address complex control tasks. In a Markov Decision Process (MDP), the framework typically …

On the use of the policy gradient and hessian in inverse reinforcement learning

AM Metelli, M Pirotta, M Restelli - Intelligenza Artificiale, 2020‏ - journals.sagepub.com
Reinforcement Learning (RL) is an effective approach to solve sequential decision making
problems when the environment is equipped with a reward function to evaluate the agent's …