ray/rllib/tuned_examples/apex_dqn/atari-apex-dqn.yaml

30 lines
873 B
YAML

apex-breakoutnoframeskip-v4:
env: BreakoutNoFrameskip-v4
run: APEX
# Minimum reward and total ts (in given time_total_s) to pass this test.
stop:
time_total_s: 7200
episode_reward_mean: 20.0
timesteps_total: 7000000
config:
double_q: false
dueling: false
num_atoms: 1
noisy: false
n_step: 3
lr: .0001
adam_epsilon: .00015
hiddens: [512]
replay_buffer_config:
capacity: 1000000
prioritized_replay_alpha: 0.5
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
min_sample_timesteps_per_iteration: 25000