2022-05-16 13:13:49 +02:00
|
|
|
apex-breakoutnoframeskip-v4:
|
|
|
|
|
env: BreakoutNoFrameskip-v4
|
|
|
|
|
run: APEX
|
|
|
|
|
# Minimum reward and total ts (in given time_total_s) to pass this test.
|
|
|
|
|
pass_criteria:
|
|
|
|
|
episode_reward_mean: 100.0
|
|
|
|
|
timesteps_total: 7000000
|
|
|
|
|
stop:
|
|
|
|
|
time_total_s: 7200
|
|
|
|
|
config:
|
|
|
|
|
double_q: false
|
|
|
|
|
dueling: false
|
|
|
|
|
num_atoms: 1
|
|
|
|
|
noisy: false
|
|
|
|
|
n_step: 3
|
|
|
|
|
lr: .0001
|
|
|
|
|
adam_epsilon: .00015
|
|
|
|
|
hiddens: [512]
|
2022-05-17 13:43:49 +02:00
|
|
|
replay_buffer_config:
|
|
|
|
|
capacity: 1000000
|
|
|
|
|
prioritized_replay_alpha: 0.5
|
2022-05-16 13:13:49 +02:00
|
|
|
exploration_config:
|
|
|
|
|
epsilon_timesteps: 200000
|
|
|
|
|
final_epsilon: 0.01
|
|
|
|
|
num_gpus: 1
|
|
|
|
|
num_workers: 8
|
|
|
|
|
num_envs_per_worker: 8
|
|
|
|
|
rollout_fragment_length: 20
|
|
|
|
|
train_batch_size: 512
|
|
|
|
|
target_network_update_freq: 50000
|
2022-06-10 17:09:18 +02:00
|
|
|
min_sample_timesteps_per_iteration: 25000
|
