tristandeleu/pytorch-maml-rl
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
PythonMIT
Issues
- 4
The progress bar doesn't increase at all
#66 opened by seolhokim - 0
After running the train.py, error "Unable to solve the normal equations in `LinearFeatureBaseline`. The matrix X^T*X (with X the design matrix) is not full-rank, regardless of the regularization (maximum regularization: 1.0)." occurs.
#72 opened by bianca-li-bupt - 0
Sync Vec porting
#70 opened by spyroot - 0
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 = ov.GetOverlappedResult(True) File "D:\Anaconda3\envs\testenv\lib\multiprocessing\connection.py", line 250, in recv buf = self._recv_bytes() File "D:\Anaconda3\envs\testenv\lib\multiprocessing\connection.py", line 321, in _recv_bytes raise EOFError EOFError BrokenPipeError: [WinError 109] I run the code on win10 but this error occurred.
#69 opened by tsinghuazl22 - 0
EOFError BrokenPipeError: [WinError 109]
#68 opened by tsinghuazl22 - 0
raise EOFError
#67 opened by tsinghuazl22 - 0
- 0
is it posible to combine DPPG with MAML?
#64 opened by whynpt - 1
- 0
- 1
- 1
how can I adapt maml on my own environment?
#59 opened by tianyma - 2
Seeing the agent in action
#27 opened by Praneethsv - 1
Can not read your env in the Jupyter
#58 opened by CeyaoZhang - 2
Memory is always increasing?
#39 opened by wang88256187 - 2
Questions about multi-gradient steps
#46 opened by HyeongYeolRyu - 4
- 1
Fails to converge on bandit tasks
#57 opened by vzhuang - 1
- 2
If I want to use the the meta-parameters to adapt to new task, what should I do?
#55 opened by GeorgeDUT - 7
- 4
- 2
Cuda Support Issue
#53 opened by imhgchoi - 3
Can this code run in win10 ?
#41 opened by wang88256187 - 2
Custom environment and baseline.fit(episodes) error
#48 opened by mfe7 - 0
Pre-trained networks
#50 opened by mfe7 - 1
pytorch 1.3 and python 3.8
#47 opened by mfe7 - 2
Questions about the MultiTaskSampler
#44 opened by chencsgit - 2
Question about the Ant env
#45 opened by jzstudent - 4
Questions about the output files
#43 opened by shiqichen17 - 9
- 5
question about test
#42 opened by Maryamr314 - 2
Interpretation of before and after update
#26 opened by navneet-nmk - 2
- 4
Restoring model
#36 opened by louiskirsch - 1
HalfCheetahDir-v1
#33 opened by huziye - 3
builtins.AttributeError: 'NoneType' object has no attribute 'timestep_limit'??
#37 opened by wang88256187 - 2
Question about regression in baseline
#35 opened by hzyjerry - 1
TabularMDP-v0 : data type not understood
#34 opened - 1
- 1
- 4
Are benchmarks available?
#29 opened by quanvuong - 2
questions about Ant environment?
#25 opened by silverbottlep - 2
- 1
log_ratio problem
#24 opened by ecada - 4
- 0
- 2
- 2
KL divergence with old policy in trpo training
#20 opened by hzyjerry - 1
Question about first_order argument
#19 opened by hzyjerry