ray/rllib/tuned_examples/ppo/pendulum-appo.yaml

pendulum-appo-vtrace:
    env: Pendulum-v0
    run: APPO
    stop:
        episode_reward_mean: -1000  # just check it learns a bit
        timesteps_total: 500000
    config:
        # Works for both torch and tf.
        framework: tf
        vtrace: true
        num_gpus: 0
        num_workers: 1
        lambda: 0.1
        gamma: 0.95
        lr: 0.0003
        train_batch_size: 100
        minibatch_buffer_size: 16
        num_sgd_iter: 10
        model:
            fcnet_hiddens: [256, 256]
        batch_mode: truncate_episodes
        observation_filter: MeanStdFilter
[RLlib] Benchmark and regression test yaml cleanup and restructuring. (#8414) 2020-05-26 11:10:27 +02:00			`pendulum-appo-vtrace:`
[rllib] Support continuous action distributions in IMPALA/APPO (#4771) 2019-05-16 22:05:07 -07:00			`env: Pendulum-v0`
			`run: APPO`
			`stop:`
[RLlib] PyTorch version of APPO. (#8120) - Translate all vtrace functionality to torch and added torch to the framework_iterator-loop in all existing vtrace test cases. - Add learning test cases for APPO torch (both w/ and w/o v-trace). - Add quick compilation tests for APPO (tf and torch, v-trace and no v-trace). 2020-04-23 09:11:12 +02:00			`episode_reward_mean: -1000 # just check it learns a bit`
[rllib] Support continuous action distributions in IMPALA/APPO (#4771) 2019-05-16 22:05:07 -07:00			`timesteps_total: 500000`
			`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] PyTorch version of APPO. (#8120) - Translate all vtrace functionality to torch and added torch to the framework_iterator-loop in all existing vtrace test cases. - Add learning test cases for APPO torch (both w/ and w/o v-trace). - Add quick compilation tests for APPO (tf and torch, v-trace and no v-trace). 2020-04-23 09:11:12 +02:00			`vtrace: true`
[rllib] Support continuous action distributions in IMPALA/APPO (#4771) 2019-05-16 22:05:07 -07:00			`num_gpus: 0`
			`num_workers: 1`
[rllib] Importance Sampling and KL Loss for APPO (#5051) 2019-07-29 15:02:32 -07:00			`lambda: 0.1`
[rllib] Support continuous action distributions in IMPALA/APPO (#4771) 2019-05-16 22:05:07 -07:00			`gamma: 0.95`
[rllib] Importance Sampling and KL Loss for APPO (#5051) 2019-07-29 15:02:32 -07:00			`lr: 0.0003`
			`train_batch_size: 100`
			`minibatch_buffer_size: 16`
			`num_sgd_iter: 10`
			`model:`
[RLlib] PyTorch version of APPO. (#8120) - Translate all vtrace functionality to torch and added torch to the framework_iterator-loop in all existing vtrace test cases. - Add learning test cases for APPO torch (both w/ and w/o v-trace). - Add quick compilation tests for APPO (tf and torch, v-trace and no v-trace). 2020-04-23 09:11:12 +02:00			`fcnet_hiddens: [256, 256]`
			`batch_mode: truncate_episodes`
[rllib] Importance Sampling and KL Loss for APPO (#5051) 2019-07-29 15:02:32 -07:00			`observation_filter: MeanStdFilter`