Commit 0fb849b2 authored by Dipam Chakraborty's avatar Dipam Chakraborty
Browse files

old hparams with ppg

parent ca30c538
......@@ -9,7 +9,7 @@ procgen-ppo:
# === Settings for Checkpoints ===
checkpoint_freq: 1
checkpoint_freq: 100
checkpoint_at_end: True
keep_checkpoints_num: 5
......@@ -29,7 +29,7 @@ procgen-ppo:
return_blind: 1
return_max: 10
gamma: 0.999
gamma: 0.996
lambda: 0.95
lr: 5.0e-4
# Number of SGD iterations in each outer loop
......@@ -46,16 +46,16 @@ procgen-ppo:
no_done_at_end: False
# Custom switches
retune_skips: 200000
retune_replay_size: 300000
retune_skips: 300000
retune_replay_size: 200000
num_retunes: 20
retune_epochs: 6
standardize_rewards: True
aux_mbsize: 512
aux_mbsize: 1024
adaptive_gamma: False
final_lr: 2.0e-4
lr_schedule: 'None'
lr_schedule: 'linear'
final_entropy_coeff: 0.002
entropy_schedule: False
......@@ -85,7 +85,7 @@ procgen-ppo:
init_normed: True
use_layernorm: False
num_workers: 4
num_workers: 7
num_envs_per_worker: 16
rollout_fragment_length: 256
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment