csingh27sewts Masterarbeit issues

csingh27sewts / Masterarbeit

0 stars 1 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Make the repository compact

#91 csingh27 opened 3 years ago
0
Create a config for cloth type / use from rlpyt

#90 csingh27 opened 3 years ago
0
Write separate function for evaluation in a separate python script

#89 csingh27 opened 3 years ago
0
Automate naming of experiment files in config

#88 csingh27 opened 3 years ago
0
Create config files for experiments

#87 csingh27 opened 3 years ago
0
Organize the experiments into categories

#86 csingh27 opened 3 years ago
0
Create config.yaml for your experiments

#85 csingh27 closed 3 years ago
0
Make a README of all experiment files for Stable Baselines Implementation

#84 csingh27sewts opened 3 years ago
0
Check cloth_sewts_minimal_1 on custom implementation

#83 csingh27sewts opened 3 years ago
0
Actor loss large even on convergence - Stable baselines cloth_sewts_minimal

#82 csingh27 closed 3 years ago
1
CUDA Initialization error Stable_baselines

#81 csingh27sewts closed 3 years ago
1
Actor_loss negative and increasing with stable_baselines implementation

#80 csingh27sewts closed 3 years ago
17
Stable baselines tensorboard event file empty

#79 csingh27sewts closed 3 years ago
2
Add logging to Stable baselines implementation

#78 csingh27sewts closed 3 years ago
0
Memory gets full error for stable baselines implementation

#77 csingh27 closed 3 years ago
4
Go for stable baselines implementation to get first results

#76 csingh27sewts closed 3 years ago
0
Custom Implementation : Solve NaN errors when action is not multiplied by 20

#75 csingh27sewts opened 3 years ago
1
Make the actor critic learn in isolation as defined in a separate network

#74 csingh27 opened 3 years ago
0
Change the neural network architecture to accomodate cloth corner with action size 7

#73 csingh27 opened 3 years ago
0
Check why actor loss, critic loss, value loss are increasing

#72 csingh27 opened 3 years ago
2
Scale actions to make them fall in the correct range for 0.05 movement of corner points.

#71 csingh27 opened 3 years ago
1
Check why action is not as expected

#70 csingh27 opened 3 years ago
0
Add a score for each episode

#69 csingh27 opened 3 years ago
0
Run original cartpole_problem, display all functions like in your implementation, by Phil, check results and compare the experiment with your experiment.

#68 csingh27 opened 3 years ago
0
Eliminate saving of unnecessary plots and checkpoints to avoid consuming too much memory while training.

#67 csingh27 closed 3 years ago
1
Add plot of average_target_value as well

#66 csingh27 closed 3 years ago
1
Make a GUI displaying reward, entropy, value, critic, actor loss, value loss, critic loss in ony pysimplegui window

#65 csingh27 closed 3 years ago
0
Checkpoints not carried forward from episode to episode

#64 csingh27 closed 3 years ago
1
Add CNN for policy network if state for cloth_corner is image

#63 csingh27 closed 3 years ago
1
Check why the cloth is pushed away towards the edge and solve it asap

#62 csingh27 opened 3 years ago
5
Modify storage of results such that they do not accumulate and cause OOM errors

#61 csingh27 closed 3 years ago
2
Print graphs using autograd pytorch

#60 csingh27 opened 3 years ago
0
Process killed error on personal laptop. (Memory leaks)

#59 csingh27 closed 3 years ago
18
Updated parameters

#58 csingh27 closed 3 years ago
0
Make a custom code using rlpyt packages

#57 csingh27 closed 3 years ago
1
Try other implementations of Soft Actor Critic

#56 csingh27 closed 3 years ago
1
Make rlpyt run on this cpu

#55 csingh27 closed 3 years ago
1
Compare parameter values with rlpyt and use all similar values for cloth_corner

#54 csingh27 closed 3 years ago
0
Redefine entropy such that the agent learns with cloth_corner

#53 csingh27 closed 3 years ago
1
Run rope environment

#52 csingh27 opened 3 years ago
0
Run rlpyt

#51 csingh27 closed 3 years ago
1
Make plots for Value Loss, Critic Loss, Actor Loss

#50 csingh27 closed 3 years ago
3
Save intermediate checkpoints

#49 csingh27 closed 3 years ago
0
Update actions to show movement in just x,y and not x,y,z

#48 csingh27 closed 3 years ago
1
Link simulation with cloth_sac_main.py

#47 csingh27 opened 3 years ago
0
Clean the repository

#46 csingh27 opened 3 years ago
0
Clean cloth_sac_main.py

#45 csingh27 opened 3 years ago
0
Adding SAC plots Fix #43, fix #42, Fix #35, Fix #34, Fix#33

#44 csingh27 closed 3 years ago
0
Add UR5 simulation file for inference

#43 csingh27 closed 3 years ago
0
Plot averages of critics, values and entropy

#42 csingh27 closed 3 years ago
0