Atari Environment Benchmark

Run Parameters
n_runs	5
n_epochs	200
n_steps	250000
n_episodes_test	125000

BreakoutDeterministic-v4

AveragedDQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_approximators: 10
  n_steps_per_fit: 4
  network: DQNNetwork
  target_update_frequency: 2500
CategoricalDQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_atoms: 51
  n_features: 512
  n_steps_per_fit: 4
  network: DQNFeatureNetwork
  target_update_frequency: 2500
  v_max: 10
  v_min: -10
DQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_steps_per_fit: 4
  network: DQNNetwork
  target_update_frequency: 2500
DoubleDQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_steps_per_fit: 4
  network: DQNNetwork
  target_update_frequency: 2500
DuelingDQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_features: 512
  n_steps_per_fit: 4
  network: DQNFeatureNetwork
  target_update_frequency: 2500
MaxminDQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_approximators: 3
  n_steps_per_fit: 4
  network: DQNNetwork
  target_update_frequency: 2500
NoisyDQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_features: 512
  n_steps_per_fit: 4
  network: DQNFeatureNetwork
  target_update_frequency: 2500
PrioritizedDQN:
  batch_size: 32
  initial_replay_size: 50000
  lr: 0.0001
  max_replay_size: 1000000
  n_steps_per_fit: 4
  network: DQNNetwork
  target_update_frequency: 2500