pytorch-maml-rl
pytorch-maml-rl copied to clipboard
tristandeleu
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
do you happen to have the hyperparameters for the multi-armed bandit experiments. im trying to compare with the results of Duan et al. 2016
Hi, I am wondering what are the effects of having `first-order=False`, and when should we use it? From what I understand of the current implementation, `first_order` only affects the sample...
after `pip install -r requirements.txt`, I ran ` python train.py --config configs/maml/halfcheetah-vel.yaml --output-folder maml-halfcheetah-vel --seed 1 --num-workers 8` but progress doesn't increase after a day. ` 0%| | 0/500 [00:00
The solution is as below. In baseline.py line 60: 1. Replace the 'torch.lstsq' with 'torch.linalg.lstsq'. Because the former function was removed. 2. Output coeffs is an instance now, not a...
Traceback (most recent call last): File "D:\Anaconda3\envs\testenv\lib\multiprocessing\process.py", line 258, in _bootstrap self.run() File "F:\aa_maml\MAML-Pytorch-RL-master\maml_rl\envs\subproc_vec_env.py", line 61, in run command, data = self.remote.recv() File "D:\Anaconda3\envs\testenv\lib\multiprocessing\connection.py", line 312, in _recv_bytes nread, err...
Traceback (most recent call last): File "D:\Anaconda3\envs\testenv\lib\multiprocessing\process.py", line 258, in _bootstrap self.run() File "F:\aa_maml\MAML-Pytorch-RL-master\maml_rl\envs\subproc_vec_env.py", line 61, in run command, data = self.remote.recv() File "D:\Anaconda3\envs\testenv\lib\multiprocessing\connection.py", line 312, in _recv_bytes nread, err...
Is there anyone met with this problem BrokenPipeError: [WinError 109] ? I had test the code on win10, is can run for a while but finally this error occur. can...
Hello, I setup code from the main branch and I get the following error for all the Gym environments in the solution: Traceback (most recent call last): File "C:\RESEARCH\APPS\pytorch-maml-rl-master\train.py", line...
Metadata
Owner
Metadata
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch