Commit 6910530d authored by manueth's avatar manueth

Experiment for deadlock reward with tree obs

parent 26f2edba
flatland-sparse-small-tree-fc-dlock-apex:
run: APEX
env: flatland_sparse
stop:
timesteps_total: 100000000 # 1e8
checkpoint_freq: 10
checkpoint_at_end: True
keep_checkpoints_num: 5
checkpoint_score_attr: episode_reward_mean
config:
num_workers: 15
num_envs_per_worker: 5
num_gpus: 1
env_config:
observation: tree
observation_config:
max_depth: 2
shortest_path_max_depth: 30
generator: sparse_rail_generator
generator_config: small_v0
resolve_deadlocks: True
deadlock_reward: -1000
wandb:
project: flatland
entity: masterscrat
tags: ["small_v0", "tree_obs_dlock", "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