1 year ago

#69678

test-img

Ashish Kumar

PPO Model not loading

I have trained an agent on colab using openAI gym and stable_baselines(PPO) but when I downloaded the model to local computer I can't load the model and it is throwing error.

model = PPO.load(TRAINED_MODEL_PATH
---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
Input In [68], in <module>
----> 1 model = PPO.load(TRAINED_MODEL_PATH)

File ~/rl/lib/python3.8/site-packages/stable_baselines3/common/base_class.py:717, in BaseAlgorithm.load(cls, path, env, device, custom_objects, print_system_info, force_reset, **kwargs)
    715 model.__dict__.update(data)
    716 model.__dict__.update(kwargs)
--> 717 model._setup_model()
    719 # put state_dicts back in place
    720 model.set_parameters(params, exact_match=True, device=device)

File ~/rl/lib/python3.8/site-packages/stable_baselines3/ppo/ppo.py:158, in PPO._setup_model(self)
    155 super(PPO, self)._setup_model()
    157 # Initialize schedules for policy/value clipping
--> 158 self.clip_range = get_schedule_fn(self.clip_range)
    159 if self.clip_range_vf is not None:
    160     if isinstance(self.clip_range_vf, (float, int)):

File ~/rl/lib/python3.8/site-packages/stable_baselines3/common/utils.py:91, in get_schedule_fn(value_schedule)
     89     value_schedule = constant_fn(float(value_schedule))
     90 else:
---> 91     assert callable(value_schedule)
     92 return value_schedule

AssertionError:

python

deep-learning

reinforcement-learning

0 Answers

Your Answer

Accepted video resources