seed: 42
env_name: CartPole-v1
train:
  nstep: ${buffer.nstep}
  timesteps: 50000
  batch_size: 128
  test_every: 2500
  eps_max: 1
  eps_min: 0.05
  eps_steps: 12500
  start_steps: 0
  plot_interval: 2000
  eval_interval: 2000
  eval_episodes: 10
agent:
  gamma: 0.99
  lr: 0.002
  tau: 0.1
  nstep: ${buffer.nstep}
  target_update_interval: 3
  hidden_size: 64
  activation:
    _target_: torch.nn.ELU
  use_dueling: false
  use_double: false
buffer:
  capacity: 50000
  use_per: false
  nstep: 1
  gamma: ${agent.gamma}
  per_alpha: 0.7
  per_beta: 0.4
  per_eps: 0.01