Open Zaibali9999 opened 1 year ago
(array([ 0.0047165 , -0.04676152, -0.03735694, -0.0472385 ], dtype=float32), {})
D:\AI\PPO\torch\ppo_torch.py:137: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\utils\tensor_new.cpp:233.)
state = T.tensor([observation], dtype=T.float).to(self.actor.device)
Traceback (most recent call last):
File "D:\AI\PPO\torch\main.py", line 31, in
same issue with torch agent
Hey Hi , I'm getting the same error:
state = T.tensor([observation], dtype=T.float).to(self.actor.device)
Traceback (most recent call last):
File "/home/rafay/RL/ReinforcementLearning/PolicyGradient/PPO/torch/main.py", line 33, in
@Zaibali9999 if you have solved the issue, can you please help me out? @philtabor please guide.
Thanks
(array([-0.02680779, 0.00466264, -0.02511859, -0.04842809], dtype=float32), {}) Traceback (most recent call last): File "main.py", line 31, in
action, prob, val = agent.choose_action(observation)
File "D:\AI\PPO\agent.py", line 41, in choose_action
state = tf.convert_to_tensor([observation],dtype=tf.float32)
File "C:\Users\Buster.conda\envs\PPO\lib\site-packages\tensorflow\python\util\traceback_utils.py", line 153, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\Buster.conda\envs\PPO\lib\site-packages\tensorflow\python\framework\constant_op.py", line 102, in convert_to_eager_tensor
return ops.EagerTensor(value, ctx.device_name, dtype)
ValueError: Can't convert non-rectangular Python sequence to Tensor.