Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
N
neurips2020-flatland-baselines
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
1
Issues
1
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Flatland
neurips2020-flatland-baselines
Commits
14da4b88
Commit
14da4b88
authored
May 12, 2020
by
MasterScrat
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Adding test configurations
parent
6407950b
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
155 additions
and
0 deletions
+155
-0
experiments/tests/MARWIL.yaml
experiments/tests/MARWIL.yaml
+65
-0
experiments/tests/conflict_obs_apex.yaml
experiments/tests/conflict_obs_apex.yaml
+33
-0
experiments/tests/global_obs_ppo.yaml
experiments/tests/global_obs_ppo.yaml
+48
-0
test.sh
test.sh
+9
-0
No files found.
experiments/tests/MARWIL.yaml
0 → 100644
View file @
14da4b88
flatland-random-sparse-small-tree-marwil-fc-ppo
:
run
:
MARWIL
env
:
flatland_random_sparse_small
stop
:
timesteps_total
:
100000
# 1e7
checkpoint_freq
:
10
checkpoint_at_end
:
True
keep_checkpoints_num
:
5
checkpoint_score_attr
:
episode_reward_mean
config
:
beta
:
0
# grid_search: [0, 1] # compare IL (beta=0) vs MARWIL
input
:
/tmp/flatland-out
# effective batch_size: train_batch_size * num_agents_in_each_environment [5, 10]
# see https://github.com/ray-project/ray/issues/4628
train_batch_size
:
1000
# 5000
rollout_fragment_length
:
50
# 100
num_workers
:
2
num_envs_per_worker
:
1
batch_mode
:
truncate_episodes
observation_filter
:
NoFilter
num_gpus
:
0
env_config
:
min_seed
:
1002
max_seed
:
213783
min_test_seed
:
0
max_test_seed
:
100
# After how many episodes the level should be regenerated:
reset_env_freq
:
1
observation
:
tree
observation_config
:
max_depth
:
2
shortest_path_max_depth
:
30
regenerate_rail_on_reset
:
True
regenerate_schedule_on_reset
:
True
render
:
False
model
:
fcnet_activation
:
relu
fcnet_hiddens
:
[
256
,
256
]
vf_share_layers
:
True
# False
# evaluation_num_workers: 1
# # Enable evaluation, once per training iteration.
# evaluation_interval: 25
# # Run 1 episode each time evaluation runs.
# evaluation_num_episodes: 1
# # Override the env config for evaluation.
# evaluation_config:
# explore: False
# env_config:
# min_seed: 1002
# max_seed: 213783
# min_test_seed: 0
# max_test_seed: 100
# # After how many episodes the level should be regenerated:
# reset_env_freq: 1
# observation: tree
# observation_config:
# max_depth: 2
# shortest_path_max_depth: 30
# regenerate_rail_on_reset: True
# regenerate_schedule_on_reset: True
# render: False
experiments/tests/conflict_obs_apex.yaml
0 → 100644
View file @
14da4b88
flatland-random-sparse-small-tree-fc-ppo
:
run
:
APEX
env
:
flatland_sparse
stop
:
timesteps_total
:
50000
checkpoint_freq
:
10
checkpoint_at_end
:
True
keep_checkpoints_num
:
5
checkpoint_score_attr
:
episode_reward_mean
config
:
num_workers
:
2
num_envs_per_worker
:
5
num_gpus
:
0
env_config
:
observation
:
localConflict
observation_config
:
max_depth
:
2
shortest_path_max_depth
:
30
n_local
:
5
generator
:
sparse_rail_generator
generator_config
:
small_v0
wandb
:
project
:
flatland
entity
:
masterscrat
tags
:
[
"
small_v0"
,
"
local_conflict_obs"
,
"
apex"
]
# TODO should be set programmatically
model
:
fcnet_activation
:
relu
fcnet_hiddens
:
[
256
,
256
]
vf_share_layers
:
True
# False
experiments/tests/global_obs_ppo.yaml
0 → 100644
View file @
14da4b88
flatland-sparse-global-conv-ppo
:
run
:
PPO
env
:
flatland_sparse
stop
:
timesteps_total
:
500
# 1e7
checkpoint_freq
:
10
checkpoint_at_end
:
True
keep_checkpoints_num
:
5
checkpoint_score_attr
:
episode_reward_mean
config
:
clip_rewards
:
True
clip_param
:
0.1
vf_clip_param
:
500.0
entropy_coeff
:
0.01
# effective batch_size: train_batch_size * num_agents_in_each_environment [5, 10]
# see https://github.com/ray-project/ray/issues/4628
train_batch_size
:
1000
# 5000
rollout_fragment_length
:
50
# 100
sgd_minibatch_size
:
100
# 500
num_sgd_iter
:
10
num_workers
:
2
num_envs_per_worker
:
2
batch_mode
:
truncate_episodes
observation_filter
:
NoFilter
vf_share_layers
:
True
vf_loss_coeff
:
0.5
num_gpus
:
0
env_config
:
observation
:
global
observation_config
:
max_width
:
32
max_height
:
32
generator
:
sparse_rail_generator
generator_config
:
small_v0
wandb
:
project
:
flatland
entity
:
masterscrat
tags
:
[
"
small_v0"
,
"
global_obs"
]
# TODO should be set programmatically
model
:
custom_model
:
global_obs_model
custom_options
:
architecture
:
impala
architecture_options
:
residual_layers
:
[[
16
,
2
],
[
32
,
4
]]
test.sh
0 → 100644
View file @
14da4b88
echo
"===================="
echo
"MARWIL"
echo
"===================="
time
python ./train.py
-f
experiments/tests/MARWIL.yaml
echo
"===================="
echo
"GLOBAL OBS"
echo
"===================="
time
python ./train.py
-f
experiments/tests/global_obs.yaml
\ No newline at end of file
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment