DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation
This provides a new tool for reinforcement learning researchers to study challenging topics, but it is incremental as it builds on existing standards like OpenAI Gym.
The authors introduced DIAMBRA Arena, a new reinforcement learning platform with high-quality environments compliant with OpenAI Gym, designed to address the need for new challenges in research. They demonstrated its utility by training agents with proximal policy optimization to achieve human-like behavior.
The recent advances in reinforcement learning have led to effective methods able to obtain above human-level performances in very complex environments. However, once solved, these environments become less valuable, and new challenges with different or more complex scenarios are needed to support research advances. This work presents DIAMBRA Arena, a new platform for reinforcement learning research and experimentation, featuring a collection of high-quality environments exposing a Python API fully compliant with OpenAI Gym standard. They are episodic tasks with discrete actions and observations composed by raw pixels plus additional numerical values, all supporting both single player and two players mode, allowing to work on standard reinforcement learning, competitive multi-agent, human-agent competition, self-play, human-in-the-loop training and imitation learning. Software capabilities are demonstrated by successfully training multiple deep reinforcement learning agents with proximal policy optimization obtaining human-like behavior. Results confirm the utility of DIAMBRA Arena as a reinforcement learning research tool, providing environments designed to study some of the most challenging topics in the field.