Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908428784369664 |
|---|---|
| author | Salaorni, Davide De Paola, Vincenzo Delpero, Samuele Dispoto, Giovanni Bonetti, Paolo Russo, Alessio Calcagno, Giuseppe Trovò, Francesco Papini, Matteo Metelli, Alberto Maria Mussi, Marco Restelli, Marcello |
| author_facet | Salaorni, Davide De Paola, Vincenzo Delpero, Samuele Dispoto, Giovanni Bonetti, Paolo Russo, Alessio Calcagno, Giuseppe Trovò, Francesco Papini, Matteo Metelli, Alberto Maria Mussi, Marco Restelli, Marcello |
| contents | In recent years, \emph{Reinforcement Learning} (RL) has made remarkable progress, achieving superhuman performance in a wide range of simulated environments. As research moves toward deploying RL in real-world applications, the field faces a new set of challenges inherent to real-world settings, such as large state-action spaces, non-stationarity, and partial observability. Despite their importance, these challenges are often underexplored in current benchmarks, which tend to focus on idealized, fully observable, and stationary environments, often neglecting to incorporate real-world complexities explicitly. In this paper, we introduce \texttt{Gym4ReaL}, a comprehensive suite of realistic environments designed to support the development and evaluation of RL algorithms that can operate in real-world scenarios. The suite includes a diverse set of tasks that expose algorithms to a variety of practical challenges. Our experimental results show that, in these settings, standard RL algorithms confirm their competitiveness against rule-based benchmarks, motivating the development of new methods to fully exploit the potential of RL to tackle the complexities of real-world tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00257 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning Salaorni, Davide De Paola, Vincenzo Delpero, Samuele Dispoto, Giovanni Bonetti, Paolo Russo, Alessio Calcagno, Giuseppe Trovò, Francesco Papini, Matteo Metelli, Alberto Maria Mussi, Marco Restelli, Marcello Machine Learning Artificial Intelligence In recent years, \emph{Reinforcement Learning} (RL) has made remarkable progress, achieving superhuman performance in a wide range of simulated environments. As research moves toward deploying RL in real-world applications, the field faces a new set of challenges inherent to real-world settings, such as large state-action spaces, non-stationarity, and partial observability. Despite their importance, these challenges are often underexplored in current benchmarks, which tend to focus on idealized, fully observable, and stationary environments, often neglecting to incorporate real-world complexities explicitly. In this paper, we introduce \texttt{Gym4ReaL}, a comprehensive suite of realistic environments designed to support the development and evaluation of RL algorithms that can operate in real-world scenarios. The suite includes a diverse set of tasks that expose algorithms to a variety of practical challenges. Our experimental results show that, in these settings, standard RL algorithms confirm their competitiveness against rule-based benchmarks, motivating the development of new methods to fully exploit the potential of RL to tackle the complexities of real-world tasks. |
| title | Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.00257 |