ray/rllib/tuned_examples/cartpole-grid-search-example.yaml

cartpole-ppo:
    env: CartPole-v0
    run: PPO
    stop:
        episode_reward_mean: 200
        time_total_s: 180
    config:
        num_workers: 2
        num_sgd_iter:
            grid_search: [1, 4]
        sgd_minibatch_size:
            grid_search: [128, 256, 512]
[rllib] Initial work on integrating hyperparameter search tool (#1107) * clean up train * update * update train script * add tuned examples * add agent catalog * add tune lib * update * fix * testS * remove * train docs * comments * todo * fix resource parsing * fix cr test * add test * try to fix travis test 2017-10-13 16:18:16 -07:00			`cartpole-ppo:`
			`env: CartPole-v0`
[tune] Support user-defined trainable functions / classes / envs with a shared object registry (#1226) 2017-11-20 17:52:43 -08:00			`run: PPO`
[rllib] Initial work on integrating hyperparameter search tool (#1107) * clean up train * update * update train script * add tuned examples * add agent catalog * add tune lib * update * fix * testS * remove * train docs * comments * todo * fix resource parsing * fix cr test * add test * try to fix travis test 2017-10-13 16:18:16 -07:00			`stop:`
			`episode_reward_mean: 200`
			`time_total_s: 180`
			`config:`
			`num_workers: 2`
			`num_sgd_iter:`
			`grid_search: [1, 4]`
[rllib] clarify train batch size for PPO (#2793) It's possible to configure PPO in a way that ends up discarding most of the samples (they are treated as "stragglers"). Add a warning when this happens, and raise an exception if the waste is particularly egregious. 2018-09-05 12:06:13 -07:00			`sgd_minibatch_size:`
[rllib] Initial work on integrating hyperparameter search tool (#1107) * clean up train * update * update train script * add tuned examples * add agent catalog * add tune lib * update * fix * testS * remove * train docs * comments * todo * fix resource parsing * fix cr test * add test * try to fix travis test 2017-10-13 16:18:16 -07:00			`grid_search: [128, 256, 512]`