dopamine online with Winfy

We have hosted the application dopamine in order to run this application in our online workstations with Wine or directly.

Quick description about dopamine:

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms. It aims to fill the need for a small, easily grokked codebase in which users can freely experiment with wild ideas (speculative research). This first version focuses on supporting the state-of-the-art, single-GPU Rainbow agent (Hessel et al., 2018) applied to Atari 2600 game-playing (Bellemare et al., 2013). Specifically, our Rainbow agent implements the three components identified as most important by Hessel et al., n-step Bellman updates, prioritized experience replay, and distributional reinforcement learning. For completeness, we also provide an implementation of DQN (Mnih et al., 2015). For additional details, please see our documentation. We provide a set of Colaboratory notebooks which demonstrate how to use Dopamine. We provide a website which displays the learning curves for all the provided agents, on all the games.

Features:

• Makes it easy for new users to run benchmark experiments
• Makes it easy for new users to try out research ideas
• Provides implementations for a few, battle-tested algorithms
• Facilitates reproducibility in results. In particular, our setup follows the recommendations given by Machado et al. (2018)
• Easy experimentation, flexible development
• Compact and reliable, as well as reproducible

Categories: