tristandeleu/pytorch-maml-rl

Issues

• The progress bar doesn't increase at all

  #66 opened 2 years ago by seolhokim
  4

• 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 a year ago by bianca-li-bupt
  0

• Sync Vec porting

  #70 opened 2 years ago 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 2 years ago by tsinghuazl22
  0

• EOFError BrokenPipeError: [WinError 109]

  #68 opened 2 years ago by tsinghuazl22
  0

• raise EOFError

  #67 opened 2 years ago by tsinghuazl22
  0

• How to solve the problem of Nan value during training?

  #65 opened 2 years ago by outshine-J
  0

• is it posible to combine DPPG with MAML?

  #64 opened 3 years ago by whynpt
  0

• where to setup render value of mujoco environment?

  #62 opened 3 years ago by 1abner1
  1

• train_returns and valid_returns seems to be equal

  #61 opened 3 years ago by magienguyen
  0

• How do you get the baseline curve in Fig5 in your paper?

  #60 opened 3 years ago by tianyma
  1

• how can I adapt maml on my own environment?

  #59 opened 3 years ago by tianyma
  1

• Seeing the agent in action

  #27 opened 5 years ago by Praneethsv
  2

• Can not read your env in the Jupyter

  #58 opened 3 years ago by CeyaoZhang
  1

• Memory is always increasing?

  #39 opened 4 years ago by wang88256187
  2

• Questions about multi-gradient steps

  #46 opened 3 years ago by HyeongYeolRyu
  2

• AttributeError: Can't pickle local object 'make_env.<locals>._make_env'

  #51 opened 4 years ago by lucifer2859
  4

• Fails to converge on bandit tasks

  #57 opened 3 years ago by vzhuang
  1

• TypeError: list indices must be integers or slices, not str

  #56 opened 3 years ago by GeorgeDUT
  1

• If I want to use the the meta-parameters to adapt to new task, what should I do?

  #55 opened 4 years ago by GeorgeDUT
  2

• if i want employe this work to a new env, what should i do

  #52 opened 4 years ago by raozhongyu
  7

• what is the mean of train_episodes and valid_episodes?

  #54 opened 4 years ago by GeorgeDUT
  4

• Cuda Support Issue

  #53 opened 4 years ago by imhgchoi
  2

• Can this code run in win10 ？

  #41 opened 4 years ago by wang88256187
  3

• Custom environment and baseline.fit(episodes) error

  #48 opened 4 years ago by mfe7
  2

• Pre-trained networks

  #50 opened 4 years ago by mfe7
  0

• pytorch 1.3 and python 3.8

  #47 opened 4 years ago by mfe7
  1

• Questions about the MultiTaskSampler

  #44 opened 4 years ago by chencsgit
  2

• Question about the Ant env

  #45 opened 4 years ago by jzstudent
  2

• Questions about the output files

  #43 opened 4 years ago by shiqichen17
  4

• "terminate called after throwing an instance of 'c10::Error'"

  #40 opened 4 years ago by wyshi
  9

• question about test

  #42 opened 4 years ago by Maryamr314
  5

• Interpretation of before and after update

  #26 opened 4 years ago by navneet-nmk
  2

• Loading Pre/Partially-Trained and Visualization

  #38 opened 4 years ago by kevslinger
  2

• Restoring model

  #36 opened 4 years ago by louiskirsch
  4

• HalfCheetahDir-v1

  #33 opened 4 years ago by huziye
  1

• builtins.AttributeError: 'NoneType' object has no attribute 'timestep_limit'？？

  #37 opened 5 years ago by wang88256187
  3

• Question about regression in baseline

  #35 opened 5 years ago by hzyjerry
  2

• TabularMDP-v0 : data type not understood

  #34 opened 5 years ago
  1

• question about /maml_rl/policies/categorical_mlp.py

  #32 opened 5 years ago by Rui-Chun
  1

• Question : hessian_vector_product in MetaLearner needed for TRPO, or MAML?

  #30 opened 5 years ago by eugval
  1

• Are benchmarks available?

  #29 opened 5 years ago by quanvuong
  4

• questions about Ant environment?

  #25 opened 5 years ago by silverbottlep
  2

• Problem with registration importing the basic modified environment

  #28 opened 5 years ago by amitfishy
  2

• log_ratio problem

  #24 opened 6 years ago by ecada
  1

• what's the purpose of len(self) in batchepisode when sample

  #22 opened 6 years ago
  4

• hyperparameters for multi-armed bandit envs

  #23 opened 6 years ago by VashishtMadhavan
  0

• clean and nice implementation, could you extend to promp

  #21 opened 6 years ago
  2

• KL divergence with old policy in trpo training

  #20 opened 6 years ago by hzyjerry
  2

• Question about first_order argument

  #19 opened 6 years ago by hzyjerry
  1