Max Lapan Shmuma

## keybase.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Shmuma
                / keybase.md
            
            
              Created
              December 7, 2018 09:53
            
          
    Keybase proof

I hereby claim:

I am shmuma on github.
I am shmuma (https://keybase.io/shmuma) on keybase.
I have a public key ASB-Udjo8uXeywt8Q8Ur3dPLK5cKWdwA8-Nog8tOPGNp8go

To claim this, I am signing this object:

  
## gist:97c7482cab4b0105c96de3ccd383c87f
>>> import torch
>>> from torch.autograd import Variable
>>> t = torch.ByteTensor([240, 240])
>>> t.sum()
480
>>> v = Variable(t)
>>> v
Variable containing:
 240
 240

## gpu_mem.py
#!/usr/bin/env python3
# test memory leak on long RNN sequences
from tqdm import tqdm
import random
import numpy as np
import itertools

import torch
import torch.optim as optim
import torch.nn as nn

## gist:eabe4e50be0773bdb8ddf2056bcc262c
https://github.com/Shmuma/rl/blob/ptan/ptan/samples/reinforce.py

## gist:7e7f4810a29bcdccb88fef4b713807c6
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_predict.ini

## gist:505d05178a53788d8284ae4061f93901
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_defend_line.ini

## gist:f04e98d875f17ecb7a5d40a3b54f37fc
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_defend_center.ini

## gist:4cf12c8cc293bf70bc95120dc41fcfc4
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_health.ini

## gist:744cf0330eaf3e4fa39a06130466c259
DQN with experience replay
Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_basic.ini

## gist:43ea4ad72e8801c5e958a15c95d80583
DQN with experience replay.

Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_corridor.ini
	>>> import torch
	>>> from torch.autograd import Variable
	>>> t = torch.ByteTensor([240, 240])
	>>> t.sum()
	480
	>>> v = Variable(t)
	>>> v
	Variable containing:
	240
	240
	#!/usr/bin/env python3
	# test memory leak on long RNN sequences
	from tqdm import tqdm
	import random
	import numpy as np
	import itertools

	import torch
	import torch.optim as optim
	import torch.nn as nn
	DQN with experience replay
	Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
	Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_predict.ini
	DQN with experience replay.

	Code: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/dqn_expreplay_doom.py
	Config: https://github.com/Shmuma/rl/blob/ptan/ptan/samples/runs/dqn_exp_doom_corridor.ini