ray/rllib/tuned_examples/impala/cartpole-impala.yaml

cartpole-impala-tf:
    env: CartPole-v0
    run: IMPALA
    stop:
        episode_reward_mean: 150
        timesteps_total: 500000
    config:
        # Works for both torch and tf.
        use_pytorch: false
        num_gpus: 0
[RLlib] IMPALA PyTorch (#8287) This PR adds an IMPALA PyTorch implementation. - adds compilation tests for LSTM and w/o LSTM. - adds learning test for CartPole. 2020-05-03 13:44:25 +02:00			`cartpole-impala-tf:`
			`env: CartPole-v0`
			`run: IMPALA`
			`stop:`
			`episode_reward_mean: 150`
			`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] IMPALA PyTorch (#8287) This PR adds an IMPALA PyTorch implementation. - adds compilation tests for LSTM and w/o LSTM. - adds learning test for CartPole. 2020-05-03 13:44:25 +02:00			`use_pytorch: false`
			`num_gpus: 0`