dopamine
dopamine copied to clipboard
google
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
I ran into a nasty memory usage error, which dopamine is already fairly well structured to take care of. The title is fairly self-explanatory, and running a simultaneous job with...
# OpenAI Gym vs TensorFlow for Deep RL Let me know if there is any APIs that support both research and production
Is there a way, or AutoML tool like Adanet/mcfly, that we can use to optimize model/parameters? [https://github.com/tensorflow/adanet](url)
Just skimmed through the Document section, couldn't find any information regarding installation in Windows 10, will this framework work for windows environment?
Hi, I want to use Dopamine with my own game environnement. I don't use asterix, pong ou atari environnement. Dopamine allows to do stuff like that ? Thanks
For Python 2.7, the __init__.py is needed for modules.
I think the replay_capacity should be to 1000? but i could't find which variable control this parameter? INFO:tensorflow:Creating MyRandomDQNAgent agent with the following parameters: INFO:tensorflow: gamma: 0.990000 INFO:tensorflow: update_horizon: 1.000000...
Paths of `atari_init_test.py` and `rainbow_agent_test.py` are changed at these commits: - `atari_init_test.py` https://github.com/google/dopamine/commit/4eec4a84bba3474ceef41cfdbbffd2cbdeab5396#diff-06dd1af46472fdc9441b7d84d2cf2403 - `rainbow_agent_test.py` https://github.com/google/dopamine/commit/4eec4a84bba3474ceef41cfdbbffd2cbdeab5396#diff-f840a06d8330e74b36dbb64f73be9267
Could you possibly comment on the difficult of getting dopamine to work with continuous action spaces? Is this something that could be done with a bit of effort, or are...
