araffin commited on
Commit
9613f2d
1 Parent(s): a884fd1

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -45,7 +45,7 @@ RL Zoo branch: `feat/gym-donkeycar`
45
  ```
46
  export AE_PATH=/path/to/match_ae-32_monaco_warren.pkl
47
  # Download model and save it into the logs/ folder
48
- python -m utils.load_from_hub --algo tqc --env donkey-warren-track-v0 -orga araffin -f logs/
49
  python enjoy.py --algo tqc --env donkey-warren-track-v0 -f logs/
50
  ```
51
 
@@ -53,7 +53,7 @@ python enjoy.py --algo tqc --env donkey-warren-track-v0 -f logs/
53
  ```
54
  python train.py --algo tqc --env donkey-warren-track-v0 -f logs/
55
  # Upload the model and generate video (when possible)
56
- python -m utils.push_to_hub --algo tqc --env donkey-warren-track-v0 -f logs/ -orga araffin
57
  ```
58
 
59
  ## Hyperparameters
@@ -61,13 +61,13 @@ python -m utils.push_to_hub --algo tqc --env donkey-warren-track-v0 -f logs/ -or
61
  OrderedDict([('batch_size', 256),
62
  ('buffer_size', 200000),
63
  ('callback',
64
- [{'utils.callbacks.ParallelTrainCallback': {'gradient_steps': 200}},
65
- 'utils.callbacks.LapTimeCallback']),
66
  ('ent_coef', 'auto'),
67
  ('env_wrapper',
68
  [{'gym.wrappers.time_limit.TimeLimit': {'max_episode_steps': 10000}},
69
  'ae.wrapper.AutoencoderWrapper',
70
- {'utils.wrappers.HistoryWrapper': {'horizon': 2}}]),
71
  ('gamma', 0.99),
72
  ('gradient_steps', 256),
73
  ('learning_rate', 0.00073),
 
45
  ```
46
  export AE_PATH=/path/to/match_ae-32_monaco_warren.pkl
47
  # Download model and save it into the logs/ folder
48
+ python -m rl_zoo3.load_from_hub --algo tqc --env donkey-warren-track-v0 -orga araffin -f logs/
49
  python enjoy.py --algo tqc --env donkey-warren-track-v0 -f logs/
50
  ```
51
 
 
53
  ```
54
  python train.py --algo tqc --env donkey-warren-track-v0 -f logs/
55
  # Upload the model and generate video (when possible)
56
+ python -m rl_zoo3.push_to_hub --algo tqc --env donkey-warren-track-v0 -f logs/ -orga araffin
57
  ```
58
 
59
  ## Hyperparameters
 
61
  OrderedDict([('batch_size', 256),
62
  ('buffer_size', 200000),
63
  ('callback',
64
+ [{'rl_zoo3.callbacks.ParallelTrainCallback': {'gradient_steps': 200}},
65
+ 'rl_zoo3.callbacks.LapTimeCallback']),
66
  ('ent_coef', 'auto'),
67
  ('env_wrapper',
68
  [{'gym.wrappers.time_limit.TimeLimit': {'max_episode_steps': 10000}},
69
  'ae.wrapper.AutoencoderWrapper',
70
+ {'rl_zoo3.wrappers.HistoryWrapper': {'horizon': 2}}]),
71
  ('gamma', 0.99),
72
  ('gradient_steps', 256),
73
  ('learning_rate', 0.00073),