general_cfg: | |
Vmax: 200 | |
Vmin: 0 | |
algo_name: RainbowDQN | |
device: cuda | |
env_name: CartPole-v1 | |
eval_eps: 10 | |
eval_per_episode: 5 | |
load_checkpoint: false | |
load_path: Train_CartPole-v1_ | |
max_steps: 200 | |
mode: train | |
n_atoms: 51 | |
new_step_api: true | |
render: false | |
save_fig: true | |
seed: 1 | |
show_fig: false | |
test_eps: 10 | |
train_eps: 100 | |
wrapper: null | |
algo_cfg: | |
Vmax: 200.0 | |
Vmin: 0.0 | |
batch_size: 64 | |
buffer_size: 100000 | |
delta_z: 4.0 | |
epsilon_decay: 500 | |
epsilon_end: 0.01 | |
epsilon_start: 0.95 | |
gamma: 0.95 | |
hidden_dim: 256 | |
lr: 0.0001 | |
memory_capacity: 10000 | |
n_step: 1 | |
num_atoms: 51 | |
support: !!python/object/apply:torch._utils._rebuild_tensor_v2 | |
- !!python/object/apply:torch.storage._load_from_bytes | |
- !!binary | | |
gAKKCmz8nEb5IGqoUBkugAJN6QMugAJ9cQAoWBAAAABwcm90b2NvbF92ZXJzaW9ucQFN6QNYDQAA | |
AGxpdHRsZV9lbmRpYW5xAohYCgAAAHR5cGVfc2l6ZXNxA31xBChYBQAAAHNob3J0cQVLAlgDAAAA | |
aW50cQZLBFgEAAAAbG9uZ3EHSwR1dS6AAihYBwAAAHN0b3JhZ2VxAGN0b3JjaApGbG9hdFN0b3Jh | |
Z2UKcQFYCQAAADEwOTE5NDU5MnECWAMAAABjcHVxA0szTnRxBFEugAJdcQBYCQAAADEwOTE5NDU5 | |
MnEBYS4zAAAAAAAAAAAAAAAAAIBAAAAAQQAAQEEAAIBBAACgQQAAwEEAAOBBAAAAQgAAEEIAACBC | |
AAAwQgAAQEIAAFBCAABgQgAAcEIAAIBCAACIQgAAkEIAAJhCAACgQgAAqEIAALBCAAC4QgAAwEIA | |
AMhCAADQQgAA2EIAAOBCAADoQgAA8EIAAPhCAAAAQwAABEMAAAhDAAAMQwAAEEMAABRDAAAYQwAA | |
HEMAACBDAAAkQwAAKEMAACxDAAAwQwAANEMAADhDAAA8QwAAQEMAAERDAABIQw== | |
- 0 | |
- !!python/tuple | |
- 51 | |
- !!python/tuple | |
- 1 | |
- false | |
- !!python/object/apply:collections.OrderedDict | |
- [] | |
target_update: 4 | |
tau: 1.0 | |
value_layers: | |
- activation: relu | |
layer_dim: | |
- n_states | |
- 256 | |
layer_type: linear | |
- activation: relu | |
layer_dim: | |
- 256 | |
- 256 | |
layer_type: linear | |
- activation: none | |
layer_dim: | |
- 256 | |
- n_actions | |
layer_type: linear | |