ElegantRL

ElegantRL copied to clipboard

AttributeError: 'AgentPPO' object has no attribute 'ClassCri'

1

While Running the last command on eRL_demo_StockTrading.ipynb on colab ```python args.init_before_training(if_main=False) args.env.draw_cumulative_return(args, torch) ``` ```error --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in () ----> 1 args.env.draw_cumulative_return(args, torch) 2 frames...

xaviruvpadhiyar98

get error message "TypeError: __init__() got an unexpected keyword argument 'if_off_policy'"

1

get error message "TypeError: __init__() got an unexpected keyword argument 'if_off_policy'" when I try to run eRL_demo_StockTrading.ipynb

larryzh

AgentPPO中的explore_one_env

1

请教下AgentPPO中的explore_one_env中的splice list 的作用是什么 ` def explore_one_env(self, env, target_step): traj_temp = list() state = self.states[0] last_done = 0 for i in range(target_step): action, noise = [ary[0] for ary in self.select_actions((state,))] next_state,...

TIANRENK

Suggestion: Create Baseline Model to compare with

1

Great library and truly enjoyed using it. Experience would be ever so slightly better with a Baseline Model made to be used to compare with the other big brothers! Thanks...

notsql

Which is the way to monitoring the training process with Tensorboard?

1

Is there any guideline on how to log training metrics to Tensorboard? Is there something similar to callback mechanism in SB 3?

trungtv

Can you provide a test demo, reproduce the optimal policy and save the video?

2

Can you provide a test demo, reproduce the optimal policy and save the video? （e.g. for LunarLanderContinuous-v2 or BipedalWalker-v3）

whyy812

Problem with running FinRL_PaperTrading_Demo.ipynb

3

First when installing FinRL ,i.e., executing !pip install git+https://github.com/AI4Finance-LLC/FinRL-Library.git I see the following error message: ERROR: pip's dependency resolver does not currently take into account all the packages that are...

augustyno

I have tried to solve this according to https://exerror.com/jsondecodeerror-expecting-value-line-1-column-1-char-0-yfinance/ but it still not work return complexjson.loads(self.text, **kwargs) File "/usr/local/Cellar/[email protected]/3.9.6/Frameworks/Python.framework/Versions/3.9/lib/python3.9/json/__init__.py", line 346, in loads return _default_decoder.decode(s) File "/usr/local/Cellar/[email protected]/3.9.6/Frameworks/Python.framework/Versions/3.9/lib/python3.9/json/decoder.py", line 337, in...

echoyes

In eRL_demo_PPOinSingleFile.py there are two _get_reward_sum_ functions: ``` def get_reward_sum_raw(self, buf_len, buf_reward, buf_mask, buf_value) -> (torch.Tensor, torch.Tensor): buf_r_sum = torch.empty(buf_len, dtype=torch.float32, device=self.device) # reward sum pre_r_sum = 0 for i...

aoshuqiu

运行程序： args=Arguments(if_on_policy=False) args.agent=AgentDDPG() env=gym.make('Pendulum-v0') env.target_reward=-200 args.env=PreprocessEnv(env=env) args.reward_scale=2**-3 args.net_dim=2**7 args.batch_size=2**7 train_and_evaluate(args) 发生错误： File "F:/engine_research_20210901/ElegantRL/ElegantRL-master/elegantrl/run.py", line 717, in demo_continuous_action train_and_evaluate(args) File "F:/engine_research_20210901/ElegantRL/ElegantRL-master/elegantrl/run.py", line 190, in train_and_evaluate steps, r_exp = update_buffer(trajectory) File "F:/engine_research_20210901/ElegantRL/ElegantRL-master/elegantrl/run.py",...

jianmingzhu