Gym Control Environments Benchmarks

Run Parameters
n_runs	25
n_epochs	10
n_steps	30000
n_episodes_test	10

Pendulum-v0

A2C:
  actor_lr: 0.0007
  batch_size: 64
  critic_lr: 0.0007
  critic_network: A2CNetwork
  ent_coeff: 0.01
  eps_actor: 0.003
  eps_critic: 1.0e-05
  max_grad_norm: 0.5
  n_features: 64
  preprocessors: null
DDPG:
  actor_lr: 0.0001
  actor_network: DDPGActorNetwork
  batch_size: 64
  critic_lr: 0.001
  critic_network: DDPGCriticNetwork
  initial_replay_size: 128
  max_replay_size: 1000000
  n_features:
  - 64
  - 64
  tau: 0.001
PPO:
  actor_lr: 0.0003
  batch_size: 64
  critic_fit_params: null
  critic_lr: 0.0003
  critic_network: TRPONetwork
  eps: 0.2
  lam: 0.95
  n_epochs_policy: 4
  n_features: 32
  n_steps_per_fit: 3000
  preprocessors: null
SAC:
  actor_lr: 0.0001
  actor_network: SACActorNetwork
  batch_size: 64
  critic_lr: 0.0003
  critic_network: SACCriticNetwork
  initial_replay_size: 128
  lr_alpha: 0.0003
  max_replay_size: 500000
  n_features: 64
  preprocessors: null
  target_entropy: null
  tau: 0.001
  warmup_transitions: 128
TD3:
  actor_lr: 0.0001
  actor_network: TD3ActorNetwork
  batch_size: 64
  critic_lr: 0.001
  critic_network: TD3CriticNetwork
  initial_replay_size: 128
  max_replay_size: 1000000
  n_features:
  - 64
  - 64
  tau: 0.001
TRPO:
  batch_size: 64
  cg_damping: 0.01
  cg_residual_tol: 1.0e-10
  critic_fit_params: null
  critic_lr: 0.0003
  critic_network: TRPONetwork
  ent_coeff: 0.0
  lam: 0.95
  max_kl: 0.01
  n_epochs_cg: 100
  n_epochs_line_search: 10
  n_features: 32
  n_steps_per_fit: 3000
  preprocessors: null

LunarLanderContinuous-v2

A2C:
  actor_lr: 0.0007
  batch_size: 64
  critic_lr: 0.0007
  critic_network: A2CNetwork
  ent_coeff: 0.01
  eps_actor: 0.003
  eps_critic: 1.0e-05
  max_grad_norm: 0.5
  n_features: 64
  preprocessors: StandardizationPreprocessor
DDPG:
  actor_lr: 0.0001
  actor_network: DDPGActorNetwork
  batch_size: 64
  critic_lr: 0.001
  critic_network: DDPGCriticNetwork
  initial_replay_size: 128
  max_replay_size: 1000000
  n_features:
  - 64
  - 64
  tau: 0.001
PPO:
  actor_lr: 0.0003
  batch_size: 64
  critic_fit_params: null
  critic_lr: 0.003
  critic_network: TRPONetwork
  eps: 0.2
  lam: 0.95
  n_epochs_policy: 4
  n_features: 32
  n_steps_per_fit: 3000
  preprocessors: StandardizationPreprocessor
SAC:
  actor_lr: 0.0001
  actor_network: SACActorNetwork
  batch_size: 64
  critic_lr: 0.0003
  critic_network: SACCriticNetwork
  initial_replay_size: 128
  lr_alpha: 0.0003
  max_replay_size: 500000
  n_features: 64
  preprocessors: null
  target_entropy: null
  tau: 0.005
  warmup_transitions: 128
TD3:
  actor_lr: 0.0001
  actor_network: TD3ActorNetwork
  batch_size: 64
  critic_lr: 0.001
  critic_network: TD3CriticNetwork
  initial_replay_size: 128
  max_replay_size: 1000000
  n_features:
  - 64
  - 64
  tau: 0.001
TRPO:
  batch_size: 64
  cg_damping: 0.01
  cg_residual_tol: 1.0e-10
  critic_fit_params: null
  critic_lr: 0.03
  critic_network: TRPONetwork
  ent_coeff: 0.0
  lam: 0.95
  max_kl: 0.01
  n_epochs_cg: 100
  n_epochs_line_search: 10
  n_features: 32
  n_steps_per_fit: 3000
  preprocessors: StandardizationPreprocessor