Reinforcement learning support Tuple or Dict observation space

I use OpenAI baseline for machine learning. Now I need reinforcement learning on a environment with a complicated state space:

observation_space = [login to view URL]([login to view URL](16),

[login to view URL](low=0, high=255))

At the state, Box contains image data and Discrete contains other data.

I want a project to implement it and write a example. You can do it on baseline or use other tools.

Habilidades: Python, Deep Learning, Machine Learning (ML), Tensorflow

Veja mais: java reinforcement learning, reinforcement learning ssh, reinforcement learning forex, multi agent reinforcement learning course, competitive multi-agent reinforcement learning, rllib, multi agent reinforcement learning python, multi agent reinforcement learning, multiagentenv, multi--agent reinforcement learning survey, multi agent reinforcement learning tutorial, reinforcement learning library java, reinforcement learning matlab, reinforcement learning software, matlab code gridworld problem reinforcement learning, reinforcement learning mt4, java source code reinforcement learning, reinforcement learning project, reinforcement learning algorithm java, cliff walking reinforcement learning matlab code

Acerca do Empregador:
( 1 comentário ) Beijing, China

ID do Projeto: #27046227

2 freelancers estão ofertando em média $150 nesse trabalho


Hello, I have master's in cybernetics and AI, and both my bachelor's and master's thesis involved use of reinforcement learning. I also have a lot of experience with deep learning using reinforcement learning outside Mais

$50 USD em 1 dia
(2 Comentários)

Hello there, I am a machine learning and data science expert with more than 8 years of experience working with clients across the globe on data science consulting and providing data driven solutions through statistica Mais

$250 USD in 15 dias
(0 Comentários)