Skip to content

wip jerk #300

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

Draft
daphne-cornelisse wants to merge 1 commit into
base: 2.0
Choose a base branch
from
Draft

wip jerk #300

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 9 additions & 9 deletions pufferlib/config/ocean/drive.ini
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ policy_name = Drive
; Set to None to disable recurrence. In case this the policy will only see
; the current observation (o_t). Set to "Recurrent" to provide the policy with
; memory through an LSTM.
rnn_name = Recurrent
rnn_name = None

[vec]
num_workers = 16
Expand All @@ -26,7 +26,7 @@ num_agents = 1024
; Options: discrete, continuous
action_type = discrete
; Options: classic, jerk
dynamics_model = classic
dynamics_model = jerk
reward_vehicle_collision = -0.5
reward_offroad_collision = -0.5
dt = 0.1
Expand Down Expand Up @@ -88,7 +88,7 @@ vf_clip_coef = 0.1999999999999999
vf_coef = 2
vtrace_c_clip = 1
vtrace_rho_clip = 1
checkpoint_interval = 1000
checkpoint_interval = 500
; Rendering options
render = True
render_interval = 1000
Expand Down Expand Up @@ -173,11 +173,11 @@ mean = 0.98
max = 0.999
scale = auto

[controlled_exp.train.goal_speed]
values = [10, 20, 30, 3]
; [controlled_exp.train.goal_speed]
; values = [10, 20, 30, 3]

[controlled_exp.train.ent_coef]
values = [0.001, 0.005, 0.01]
[controlled_exp.env.dt]
values = [0.3, 0.2, 0.1, 0.4, 0.5]

[controlled_exp.train.seed]
values = [42, 55, 1]
; [controlled_exp.train.seed]
; values = [42, 55, 1]
Loading