DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation

TL;DR

DIAMBRA Arena is a versatile reinforcement learning platform with diverse environments supporting various learning paradigms, enabling advanced research and experimentation in complex scenarios.

Contribution

It introduces a new RL platform with high-quality, multi-mode environments fully compatible with OpenAI Gym, supporting research in multi-agent, human-in-the-loop, and imitation learning.

Findings

Successfully trained deep RL agents with human-like behavior

Demonstrated platform's capability for complex RL research

Supports multiple learning paradigms and competitive scenarios

Abstract

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.