Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
rical730 f5a0d0d0d1 | 3 years ago | |
---|---|---|
.. | ||
.benchmark | 5 years ago | |
README.md | 3 years ago | |
actor.py | 4 years ago | |
atari_agent.py | 3 years ago | |
atari_model.py | 4 years ago | |
ga3c_config.py | 4 years ago | |
train.py | 3 years ago |
Based on PARL, the GA3C algorithm of deep reinforcement learning has been reproduced, reaching the same level of indicators as the paper in Atari benchmarks.
Original paper: GA3C: GPU-based A3C for Deep Reinforcement Learning
A hybrid CPU/GPU version of the Asynchronous Advantage Actor-Critic (A3C) algorithm.
Please see here to know more about Atari games.
Results with one learner (in a P40 GPU) and 24 simulators (in 12 CPU) in 10 million sample steps.
At first, We can start a local cluster with 24 CPUs:
xparl start --port 8010 --cpu_num 24
Note that if you have started a master before, you don't have to run the above
command. For more information about the cluster, please refer to our
documentation
Then we can start the distributed training by running:
python train.py
[Tips] The performance can be influenced dramatically in a slower computational
environment, especially when training with low-speed CPUs. It may be caused by
the policy-lag problem.
PARL 是一个高性能、灵活的强化学习框架
Python C++ JavaScript Markdown Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》