ray/rllib/tuned_examples/ars/swimmer-ars.yaml

# can expect improvement to -140 reward in ~300-500k timesteps
swimmer-ars:
    env: Swimmer-v2
    run: ARS
    config:
        # Works for both torch and tf.
        framework: tf
        noise_stdev: 0.01
        num_rollouts: 1
        rollouts_used: 1
        num_workers: 1
        sgd_stepsize: 0.02
        noise_size: 250000000
        eval_prob: 0.2
        offset: 0
        observation_filter: NoFilter
        report_length: 3
        model:
            fcnet_hiddens: []  # a linear policy
[rllib] Fix filter sync for ES and ARS (#2918) 2018-11-06 17:09:34 -10:00			`# can expect improvement to -140 reward in ~300-500k timesteps`
[rllib] Use SGD optimizer for ARS (#2916) 2018-09-26 22:32:26 -07:00			`swimmer-ars:`
[rllib] add augmented random search (#2714) * added ars * functioning ars with regression test * added regression tests for ARs * fixed default config for ARS * ARS code runs, now time to test * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * pep8 fixes * removed unused linear model * address comments * more fixing comments * post yapf * fixed support failure * Update LICENSE * Update policies.py * Update test_supported_spaces.py * Update policies.py * Update LICENSE * Update test_supported_spaces.py * Update policies.py * Update policies.py * Update filter.py 2018-08-24 22:20:02 -07:00			`env: Swimmer-v2`
			`run: ARS`
			`config:`
[RLlib] Benchmark and regression test yaml cleanup and restructuring. (#8414) 2020-05-26 11:10:27 +02:00			`# Works for both torch and tf.`
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520) 2020-05-27 16:19:13 +02:00			`framework: tf`
[rllib] add augmented random search (#2714) * added ars * functioning ars with regression test * added regression tests for ARs * fixed default config for ARS * ARS code runs, now time to test * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * pep8 fixes * removed unused linear model * address comments * more fixing comments * post yapf * fixed support failure * Update LICENSE * Update policies.py * Update test_supported_spaces.py * Update policies.py * Update LICENSE * Update test_supported_spaces.py * Update policies.py * Update policies.py * Update filter.py 2018-08-24 22:20:02 -07:00			`noise_stdev: 0.01`
[rllib] Use SGD optimizer for ARS (#2916) 2018-09-26 22:32:26 -07:00			`num_rollouts: 1`
			`rollouts_used: 1`
[rllib] add augmented random search (#2714) * added ars * functioning ars with regression test * added regression tests for ARs * fixed default config for ARS * ARS code runs, now time to test * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * pep8 fixes * removed unused linear model * address comments * more fixing comments * post yapf * fixed support failure * Update LICENSE * Update policies.py * Update test_supported_spaces.py * Update policies.py * Update LICENSE * Update test_supported_spaces.py * Update policies.py * Update policies.py * Update filter.py 2018-08-24 22:20:02 -07:00			`num_workers: 1`
[rllib] Use SGD optimizer for ARS (#2916) 2018-09-26 22:32:26 -07:00			`sgd_stepsize: 0.02`
[rllib] add augmented random search (#2714) * added ars * functioning ars with regression test * added regression tests for ARs * fixed default config for ARS * ARS code runs, now time to test * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * ARS working and tested, changed std deviation of meanstd filter to initialize to 1 * pep8 fixes * removed unused linear model * address comments * more fixing comments * post yapf * fixed support failure * Update LICENSE * Update policies.py * Update test_supported_spaces.py * Update policies.py * Update LICENSE * Update test_supported_spaces.py * Update policies.py * Update policies.py * Update filter.py 2018-08-24 22:20:02 -07:00			`noise_size: 250000000`
			`eval_prob: 0.2`
			`offset: 0`
[rllib] Use SGD optimizer for ARS (#2916) 2018-09-26 22:32:26 -07:00			`observation_filter: NoFilter`
			`report_length: 3`
[rllib] Propagate model options correctly in ARS / ES, to action dist of PPO (#2974) * fix * fix * fix it * propagate conf to action dist * move carla example too * rr * Update policies.py * wip * lint 2018-10-01 12:49:39 -07:00			`model:`
			`fcnet_hiddens: [] # a linear policy`