Skip to content

[NOMERG] PPO update #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vmoens wants to merge 4 commits into
base: main
Choose a base branch
from
Open

[NOMERG] PPO update #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8d548c8
init
vmoens Jan 18, 2023
ccd597e
init
vmoens Jan 31, 2023
4784bdb
amend
vmoens Jan 31, 2023
b0837e6
amend
vmoens Feb 6, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 10 additions & 8 deletions ppo_pong/conf.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,28 +1,30 @@
# Logger
experiment_name: atari_pong
agent_name: ppo_agent
wandb_key: null
entity: vmoens
wandb_key: d0bee782a83f90cbc11177e36a092de77585cbb3
log_dir: /tmp/atari_pong

# Environment
env_name: PongNoFrameskip-v4
env_name: ALE/Pong-v5
frame_skip: 4

# Collector
total_frames: 40_000_000 # without accounting for frame skip
num_parallel_envs: 8
steps_per_env: 128 # between network updates
num_parallel_envs: 16
steps_per_env: 256 # between network updates

# Loss
gamma: 0.99
clip_epsilon: 0.1
clip_epsilon: 0.2
loss_critic_type: l2
entropy_coef: 0.0001
entropy_coef: 0.001
critic_coef: 1.0
gae_lamdda: 0.95
clip_grad: 0.5

# Training loop
lr: 2.5e-4
num_ppo_epochs: 3
mini_batch_size: 256 # so 4 mini_batches - (8 * 128) / 256
evaluation_frequency: 100 # In number of network updates
mini_batch_size: 128 # so 4 mini_batches - (8 * 128) / 256
evaluation_frequency: 500 # In number of network updates
Loading