Skip to content

MountainCar_DQN #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
GeYuhong wants to merge 3 commits into
base: master
Choose a base branch
from
Open

MountainCar_DQN #37

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1da6e5b
MountainCar_DQN
Apr 4, 2023
8427741
add contributor
Apr 4, 2023
f6c7aa7
Update README.md
GeYuhong Apr 4, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 44 additions & 0 deletions joyrl/benchmarks/Test_MountainCar-v0_DQN_20230404-134035/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
general_cfg:
algo_name: DQN
device: cpu
env_name: MountainCar-v0
eval_eps: 10
eval_per_episode: 5
load_checkpoint: true
load_path: Train_MountainCar-v0_DQN_20230404-130132
max_steps: 200
mode: test
new_step_api: true
render: true
render_mode: human
save_fig: true
seed: 1
show_fig: false
test_eps: 20
train_eps: 300
wrapper: null
algo_cfg:
batch_size: 64
buffer_size: 50000
epsilon_decay: 1000
epsilon_end: 0.01
epsilon_start: 0.99
gamma: 0.99
lr: 0.01
target_update: 4
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
60 changes: 60 additions & 0 deletions joyrl/benchmarks/Test_MountainCar-v0_DQN_20230404-134035/logs/log.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
2023-04-04 13:40:35 - r - INFO: - Hyperparameters:
2023-04-04 13:40:35 - r - INFO: - ================================================================================
2023-04-04 13:40:35 - r - INFO: - Name Value Type
2023-04-04 13:40:35 - r - INFO: - env_name MountainCar-v0 <class 'str'>
2023-04-04 13:40:35 - r - INFO: - new_step_api 1 <class 'bool'>
2023-04-04 13:40:35 - r - INFO: - wrapper None <class 'str'>
2023-04-04 13:40:35 - r - INFO: - render 1 <class 'bool'>
2023-04-04 13:40:35 - r - INFO: - algo_name DQN <class 'str'>
2023-04-04 13:40:35 - r - INFO: - mode test <class 'str'>
2023-04-04 13:40:35 - r - INFO: - seed 1 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - device cpu <class 'str'>
2023-04-04 13:40:35 - r - INFO: - train_eps 300 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - test_eps 20 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - eval_eps 10 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - eval_per_episode 5 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - max_steps 200 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - load_checkpoint 1 <class 'bool'>
2023-04-04 13:40:35 - r - INFO: - load_path Train_MountainCar-v0_DQN_20230404-130132 <class 'str'>
2023-04-04 13:40:35 - r - INFO: - show_fig 0 <class 'bool'>
2023-04-04 13:40:35 - r - INFO: - save_fig 1 <class 'bool'>
2023-04-04 13:40:35 - r - INFO: - render_mode human <class 'str'>
2023-04-04 13:40:35 - r - INFO: - epsilon_start 0.99 <class 'float'>
2023-04-04 13:40:35 - r - INFO: - epsilon_end 0.01 <class 'float'>
2023-04-04 13:40:35 - r - INFO: - epsilon_decay 1000 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - gamma 0.99 <class 'float'>
2023-04-04 13:40:35 - r - INFO: - lr 0.01 <class 'float'>
2023-04-04 13:40:35 - r - INFO: - buffer_size 50000 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - batch_size 64 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - target_update 4 <class 'int'>
2023-04-04 13:40:35 - r - INFO: - 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'}] <class 'str'>
2023-04-04 13:40:35 - r - INFO: - task_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Test_MountainCar-v0_DQN_20230404-134035 <class 'str'>
2023-04-04 13:40:35 - r - INFO: - model_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Test_MountainCar-v0_DQN_20230404-134035/models <class 'str'>
2023-04-04 13:40:35 - r - INFO: - res_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Test_MountainCar-v0_DQN_20230404-134035/results <class 'str'>
2023-04-04 13:40:35 - r - INFO: - log_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Test_MountainCar-v0_DQN_20230404-134035/logs <class 'str'>
2023-04-04 13:40:35 - r - INFO: - traj_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Test_MountainCar-v0_DQN_20230404-134035/traj <class 'str'>
2023-04-04 13:40:35 - r - INFO: - ================================================================================
2023-04-04 13:40:35 - r - INFO: - n_states: 2, n_actions: 3
2023-04-04 13:40:35 - r - INFO: - Start testing!
2023-04-04 13:40:35 - r - INFO: - Env: MountainCar-v0, Algorithm: DQN, Device: cpu
2023-04-04 13:40:40 - r - INFO: - Episode: 1/20, Reward: -112.000, Step: 112
2023-04-04 13:40:43 - r - INFO: - Episode: 2/20, Reward: -112.000, Step: 112
2023-04-04 13:40:47 - r - INFO: - Episode: 3/20, Reward: -112.000, Step: 112
2023-04-04 13:40:51 - r - INFO: - Episode: 4/20, Reward: -112.000, Step: 112
2023-04-04 13:40:55 - r - INFO: - Episode: 5/20, Reward: -112.000, Step: 112
2023-04-04 13:40:58 - r - INFO: - Episode: 6/20, Reward: -112.000, Step: 112
2023-04-04 13:41:02 - r - INFO: - Episode: 7/20, Reward: -112.000, Step: 112
2023-04-04 13:41:06 - r - INFO: - Episode: 8/20, Reward: -112.000, Step: 112
2023-04-04 13:41:10 - r - INFO: - Episode: 9/20, Reward: -112.000, Step: 112
2023-04-04 13:41:13 - r - INFO: - Episode: 10/20, Reward: -112.000, Step: 112
2023-04-04 13:41:17 - r - INFO: - Episode: 11/20, Reward: -112.000, Step: 112
2023-04-04 13:41:21 - r - INFO: - Episode: 12/20, Reward: -112.000, Step: 112
2023-04-04 13:41:24 - r - INFO: - Episode: 13/20, Reward: -112.000, Step: 112
2023-04-04 13:41:28 - r - INFO: - Episode: 14/20, Reward: -112.000, Step: 112
2023-04-04 13:41:32 - r - INFO: - Episode: 15/20, Reward: -112.000, Step: 112
2023-04-04 13:41:36 - r - INFO: - Episode: 16/20, Reward: -112.000, Step: 112
2023-04-04 13:41:39 - r - INFO: - Episode: 17/20, Reward: -112.000, Step: 112
2023-04-04 13:41:43 - r - INFO: - Episode: 18/20, Reward: -112.000, Step: 112
2023-04-04 13:41:47 - r - INFO: - Episode: 19/20, Reward: -112.000, Step: 112
2023-04-04 13:41:51 - r - INFO: - Episode: 20/20, Reward: -112.000, Step: 112
2023-04-04 13:41:51 - r - INFO: - Finish testing!
Binary file added joyrl/benchmarks/Test_MountainCar-v0_DQN_20230404-134035/models/checkpoint.pt
View file
Open in desktop
Binary file not shown.
Binary file added ...l/benchmarks/Test_MountainCar-v0_DQN_20230404-134035/results/learning_curve.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
21 changes: 21 additions & 0 deletions joyrl/benchmarks/Test_MountainCar-v0_DQN_20230404-134035/results/res.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
episodes,rewards,steps
0,-112.0,112
1,-112.0,112
2,-112.0,112
3,-112.0,112
4,-112.0,112
5,-112.0,112
6,-112.0,112
7,-112.0,112
8,-112.0,112
9,-112.0,112
10,-112.0,112
11,-112.0,112
12,-112.0,112
13,-112.0,112
14,-112.0,112
15,-112.0,112
16,-112.0,112
17,-112.0,112
18,-112.0,112
19,-112.0,112
43 changes: 43 additions & 0 deletions joyrl/benchmarks/Train_MountainCar-v0_DQN_20230404-130132/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
general_cfg:
algo_name: DQN
device: cpu
env_name: MountainCar-v0
eval_eps: 10
eval_per_episode: 5
load_checkpoint: false
load_path: tasks
max_steps: 200
mode: train
new_step_api: true
render: false
save_fig: true
seed: 1
show_fig: false
test_eps: 20
train_eps: 300
wrapper: null
algo_cfg:
batch_size: 64
buffer_size: 50000
epsilon_decay: 1000
epsilon_end: 0.01
epsilon_start: 0.99
gamma: 0.99
lr: 0.01
target_update: 4
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
Loading