config.yaml

defaults:
  - override hydra/launcher: submitit_local

# task settings
task: quadruped_walk
frame_stack: 3
action_repeat: 2
discount: 0.99
# train settings
num_train_frames: 1010000
num_seed_frames: 4000
# eval
eval_every_frames: 10000
num_eval_episodes: 10
# snapshot
save_snapshot: false
save_snapshot_buf: true
# replay buffer
replay_buffer_size: 1000000
replay_buffer_num_workers: 4
nstep: 3
batch_size: 256
# misc
seed: 1
device: cuda
save_video: true
save_train_video: false
use_tb: false
# experiment
experiment: exp

agent:
  _target_: drqv2.DrQV2Agent
  obs_shape: ??? # to be specified later
  action_shape: ??? # to be specified later
  device: ${device}
  lr: 1e-4
  critic_target_tau: 0.01
  update_every_steps: 2
  use_tb: ${use_tb}
  num_expl_steps: 2000
  hidden_dim: 1024
  feature_dim: 50
  stddev_schedule: 'linear(1.0,0.1,500000)'
  stddev_clip: 0.3
  pnorm_critic: false
  pnorm_actor: false
  asymmetric_clip: false
  action_penalty: null
  cpc_until: null

hydra:
  run:
    dir: ./exp_local/${now:%Y.%m.%d}/${now:%H%M%S}_${hydra.job.override_dirname}
  sweep:
    dir: ./batch_runs/${experiment}
    subdir: ${hydra.job.num}
  launcher:
    timeout_min: 4300
    cpus_per_task: 10
    gpus_per_node: 1
    tasks_per_node: 1
    mem_gb: 160
    nodes: 1
    submitit_folder: ./exp/${now:%Y.%m.%d}/${now:%H%M%S}_${experiment}/.slurm