Config file - Githubissues

internetcoffeephone commented 5 years ago

Implemented the config file as mentioned in https://github.com/eugenevinitsky/sequential_social_dilemma_games/issues/151.

4 questions:

All run scripts work, except train_baseline_actions_dqn, I presume you're working on a private/unpushed ray branch?
Currently wondering: should we get rid of tf.app.flags and retrieve values from the dictionary created by config_parser directly?
tf.app.flags adds the benefit of command line arguments, are you currently using those?
Some parameters have not been implemented/are commented out, specifically the redis/memory/debug parameters. Either the debug flag is not needed anymore, or would you prefer debug-specific values for these parameters?

I haven't reproduced the results from the paper yet. Currently it takes me 6 days to take the 3e8 steps required per experiment - I'm in the process of requesting more powerful hardware.

internetcoffeephone commented 5 years ago

Additionally, I imagine some train_* files can be merged when parametrized, there's a lot of duplicate code in there. Separating the experiment categories (baseline, visible actions, influence, moa) from their algorithms (A3C, A2C, DQN) so they can vary independently would be ideal, although I'm not sure whether it's easy to do.

internetcoffeephone commented 4 years ago

These changes are all very outdated, and I'm getting rid of config_parser in my fork. Thus, closing.

eugenevinitsky / sequential_social_dilemma_games

Config file #153