Scenic4rl: Programmatic modeling and generation of reinforcement learning environments

AS Azad, E Kim, Q Wu, K Lee, I Stoica, P Abbeel… - arXiv preprint arXiv …, 2021 - arxiv.org
The capability of a reinforcement learning (RL) agent heavily depends on the diversity of the
learning scenarios generated by the environment. Generation of diverse realistic scenarios
is challenging for real-time strategy (RTS) environments. The RTS environments are
characterized by intelligent entities/non-RL agents cooperating and competing with the RL
agents with large state and action spaces over a long period of time, resulting in an infinite
space of feasible, but not necessarily realistic, scenarios involving complex interaction …

Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments

A Salam Azad, E Kim, Q Wu, K Lee, I Stoica… - arXiv e …, 2021 - ui.adsabs.harvard.edu
The capability of a reinforcement learning (RL) agent heavily depends on the diversity of the
learning scenarios generated by the environment. Generation of diverse realistic scenarios
is challenging for real-time strategy (RTS) environments. The RTS environments are
characterized by intelligent entities/non-RL agents cooperating and competing with the RL
agents with large state and action spaces over a long period of time, resulting in an infinite
space of feasible, but not necessarily realistic, scenarios involving complex interaction …
Showing the best results for this search. See all results