Commit ecbaf734 authored by nilabha's avatar nilabha

Add global obs and local conflict configs in baseline

parent aa743b8d
Pipeline #5295 failed with stage
in 2 minutes and 42 seconds
flatland-sparse-global-conv-ppo:
run: PPO
env: flatland_sparse
stop:
timesteps_total: 15000000 # 1.5e7
checkpoint_freq: 50
checkpoint_at_end: True
keep_checkpoints_num: 100
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: 13
num_envs_per_worker: 5
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-paper
entity: aicrowd
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]]
flatland-random-sparse-small-tree-fc-ppo:
run: APEX
env: flatland_sparse
stop:
timesteps_total: 15000000 # 1.5e7
checkpoint_freq: 50
checkpoint_at_end: True
keep_checkpoints_num: 100
checkpoint_score_attr: episode_reward_mean
config:
num_workers: 13
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-paper
entity: aicrowd
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
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