Commit 19f6ab29 authored by Dipam Chakraborty's avatar Dipam Chakraborty
Browse files

submit oct 29

parent 37f363aa
...@@ -59,7 +59,7 @@ procgen-ppo: ...@@ -59,7 +59,7 @@ procgen-ppo:
augment_randint_num: 3 ## Hacky name fix later augment_randint_num: 3 ## Hacky name fix later
aux_lr: 5.0e-4 aux_lr: 5.0e-4
value_lr: 1.0e-3 value_lr: 1.0e-3
same_lr_everywhere: False same_lr_everywhere: True
aux_phase_mixed_precision: True aux_phase_mixed_precision: True
single_optimizer: False single_optimizer: False
max_time: 7200 max_time: 7200
......
...@@ -46,15 +46,15 @@ procgen-ppo: ...@@ -46,15 +46,15 @@ procgen-ppo:
no_done_at_end: False no_done_at_end: False
# Custom switches # Custom switches
retune_skips: 100000 retune_skips: 350000
retune_replay_size: 450000 retune_replay_size: 200000
num_retunes: 13 num_retunes: 13
retune_epochs: 3 retune_epochs: 6
standardize_rewards: True standardize_rewards: True
scale_reward: 1.0 scale_reward: 1.0
return_reset: False return_reset: False
aux_phase_mixed_precision: True aux_phase_mixed_precision: True
max_time: 1000000 max_time: 7200
adaptive_gamma: False adaptive_gamma: False
final_lr: 5.0e-5 final_lr: 5.0e-5
......
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