Commit fff06d4e authored by nilabha's avatar nilabha

update apex IL configs for runnign baselines

parent 28fbca16
Pipeline #4995 failed with stage
in 2 minutes
flatland-random-sparse-small-tree-fc-apex-il-loss:
run: APEX
env: flatland_sparse
stop:
timesteps_total: 1000000000 # 1e9
checkpoint_freq: 50
checkpoint_at_end: True
keep_checkpoints_num: 100
checkpoint_score_attr: episode_reward_mean
num_samples: 3
config:
input:
"/tmp/flatland-out": 0.25
sampler: 0.75
num_workers: 13
num_envs_per_worker: 1
num_gpus: 0
env_config:
observation: tree
observation_config:
max_depth: 2
shortest_path_max_depth: 30
generator: sparse_rail_generator
generator_config: small_v0
wandb:
project: flatland-paper
entity: aicrowd
tags: ["small_v0", "tree_obs", "APEX_IL_Loss"] # TODO should be set programmatically
model:
custom_model: custom_loss_model
fcnet_activation: relu
fcnet_hiddens: [256, 256]
vf_share_layers: True # False
custom_options:
input_files: /tmp/flatland-out
expert_size: 1
loss:
grid_search: [dqfd,ce,kl] # ce (cross entropy), kl (kl divergence)
lambda1: 1
lambda2: 1
\ No newline at end of file
flatland-random-sparse-small-tree-fc-apex-il-loss:
run: APEX
env: flatland_sparse
stop:
timesteps_total: 1000000000 # 1e9
checkpoint_freq: 50
checkpoint_at_end: True
keep_checkpoints_num: 100
checkpoint_score_attr: episode_reward_mean
num_samples: 3
config:
input: "/tmp/flatland-out"
input_evaluation: [is, wis, simulation]
num_workers: 13
num_envs_per_worker: 5
num_gpus: 0
env_config:
observation: tree
observation_config:
max_depth: 2
shortest_path_max_depth: 30
generator: sparse_rail_generator
generator_config: small_v0
wandb:
project: flatland-paper
entity: aicrowd
tags: ["small_v0", "tree_obs", "APEX_PURE_IL"] # TODO should be set programmatically
model:
fcnet_activation: relu
fcnet_hiddens: [256, 256]
vf_share_layers: True # False
\ No newline at end of file
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