Skip to content

[refactor] Remove nonfunctional output_path option from TrainerSettings #4087

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

Merged
merged 5 commits into from
Jun 9, 2020
Merged

[refactor] Remove nonfunctional output_path option from TrainerSettings #4087

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1519027
Remove output path from YAML configs
Jun 5, 2020
4d4e1ea
Make output path a parameter and not TrainerSettings
Jun 5, 2020
889be8e
Reverse order of params for NNPolicy
Jun 5, 2020
69ea80b
Fix tests
Jun 5, 2020
4856cc1
Fix trainer util test
Jun 6, 2020
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
1 change: 0 additions & 1 deletion config/imitation/CrawlerStatic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
use_actions: false
use_vail: false
demo_path: Project/Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawlerSta.demo
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/imitation/FoodCollector.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
use_actions: false
use_vail: false
demo_path: Project/Assets/ML-Agents/Examples/FoodCollector/Demos/ExpertFood.demo
output_path: default
keep_checkpoints: 5
max_steps: 2000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/imitation/Hallway.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,6 @@ behaviors:
use_actions: false
use_vail: false
demo_path: Project/Assets/ML-Agents/Examples/Hallway/Demos/ExpertHallway.demo
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/imitation/PushBlock.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
use_actions: false
use_vail: false
demo_path: Project/Assets/ML-Agents/Examples/PushBlock/Demos/ExpertPush.demo
output_path: default
keep_checkpoints: 5
max_steps: 15000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/ppo/3DBall.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/3DBallHard.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 5000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/3DBall_randomize.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/Basic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.9
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 3
Expand Down
1 change: 0 additions & 1 deletion config/ppo/Bouncer.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 4000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/ppo/CrawlerDynamic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/CrawlerStatic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/FoodCollector.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 2000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/ppo/GridWorld.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.9
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 5
Expand Down
1 change: 0 additions & 1 deletion config/ppo/Hallway.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/ppo/PushBlock.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 2000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/ppo/Pyramids.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
strength: 0.02
encoding_size: 256
learning_rate: 0.0003
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 128
Expand Down
1 change: 0 additions & 1 deletion config/ppo/Reacher.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 20000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/SoccerTwos.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 50000000
time_horizon: 1000
Expand Down
2 changes: 0 additions & 2 deletions config/ppo/StrikersVsGoalie.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 50000000
time_horizon: 1000
Expand Down Expand Up @@ -52,7 +51,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 50000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/Tennis.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 50000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/VisualHallway.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/ppo/VisualPushBlock.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 3000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/ppo/VisualPyramids.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
strength: 0.01
encoding_size: 256
learning_rate: 0.0003
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 128
Expand Down
1 change: 0 additions & 1 deletion config/ppo/WalkerDynamic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 25000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/WalkerStatic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 20000000
time_horizon: 1000
Expand Down
2 changes: 0 additions & 2 deletions config/ppo/WallJump.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 20000000
time_horizon: 128
Expand All @@ -45,7 +44,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 5000000
time_horizon: 128
Expand Down
2 changes: 0 additions & 2 deletions config/ppo/WallJump_curriculum.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 20000000
time_horizon: 128
Expand All @@ -45,7 +44,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 5000000
time_horizon: 128
Expand Down
1 change: 0 additions & 1 deletion config/ppo/WormDynamic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 3500000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/ppo/WormStatic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 3500000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/sac/3DBall.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/sac/3DBallHard.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/sac/Basic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 10
Expand Down
1 change: 0 additions & 1 deletion config/sac/Bouncer.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 1000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/sac/CrawlerDynamic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 5000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/sac/CrawlerStatic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 3000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/sac/FoodCollector.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 2000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/sac/GridWorld.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.9
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 500000
time_horizon: 5
Expand Down
1 change: 0 additions & 1 deletion config/sac/Hallway.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 5000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/sac/PushBlock.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 2000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/sac/Pyramids.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@ behaviors:
use_actions: true
use_vail: false
demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 128
Expand Down
1 change: 0 additions & 1 deletion config/sac/Reacher.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 20000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/sac/Tennis.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 20000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/sac/VisualHallway.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/sac/VisualPushBlock.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ behaviors:
extrinsic:
gamma: 0.99
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 3000000
time_horizon: 64
Expand Down
1 change: 0 additions & 1 deletion config/sac/VisualPyramids.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@ behaviors:
use_actions: true
use_vail: false
demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
output_path: default
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 128
Expand Down
1 change: 0 additions & 1 deletion config/sac/WalkerDynamic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 15000000
time_horizon: 1000
Expand Down
1 change: 0 additions & 1 deletion config/sac/WalkerStatic.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ behaviors:
extrinsic:
gamma: 0.995
strength: 1.0
output_path: default
keep_checkpoints: 5
max_steps: 20000000
time_horizon: 1000
Expand Down
Loading