ray/rllib/tuned_examples/a2c/cartpole-a2c-microbatch.yaml

cartpole-a2c-microbatch:
    env: CartPole-v0
    run: A2C
    stop:
        episode_reward_mean: 150
        timesteps_total: 1000000
    config:
        # Works for both torch and tf.
        framework: tf
        num_workers: 2
        gamma: 0.95
        rollout_fragment_length: 20
        microbatch_size: 40
        train_batch_size: 120
[RLlib] Benchmark and regression test yaml cleanup and restructuring. (#8414) 2020-05-26 11:10:27 +02:00			`cartpole-a2c-microbatch:`
[rllib] Add microbatch optimizer with A2C example (#6161) 2019-11-14 12:14:00 -08:00			`env: CartPole-v0`
			`run: A2C`
			`stop:`
[RLlib] Benchmark and regression test yaml cleanup and restructuring. (#8414) 2020-05-26 11:10:27 +02:00			`episode_reward_mean: 150`
[RLlib] Unflake some CI-tests. (#25313) 2022-06-03 14:51:50 +02:00			`timesteps_total: 1000000`
[rllib] Add microbatch optimizer with A2C example (#6161) 2019-11-14 12:14:00 -08:00			`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] A2C `training_iteration` method implementation (`_disable_execution_plan_api=True`) (#23735) 2022-04-15 18:36:13 +02:00			`num_workers: 2`
[rllib] Add microbatch optimizer with A2C example (#6161) 2019-11-14 12:14:00 -08:00			`gamma: 0.95`
[RLlib] A2C `training_iteration` method implementation (`_disable_execution_plan_api=True`) (#23735) 2022-04-15 18:36:13 +02:00			`rollout_fragment_length: 20`
			`microbatch_size: 40`
			`train_batch_size: 120`