CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-02-13 15:27:48 +08:00
Code Issues Projects Releases Wiki Activity

Merge pull request #354 from andywalner/random-int-fix

Browse Source 
change int to float
This commit is contained in:
Thomas Simonini
2023-06-26 17:04:37 +02:00
committed by GitHub
parent c56b59bb85 255112a2eb
commit ad5c4ebacd
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
notebooks/unit2/unit2.ipynb
View File

@@ -695,9 +695,9 @@
"source": [
"def epsilon_greedy_policy(Qtable, state, epsilon):\n",
" # Randomly generate a number between 0 and 1\n",
" random_int = random.uniform(0,1)\n",
" # if random_int > greater than epsilon --> exploitation\n",
" if random_int > epsilon:\n",
" random_num = random.uniform(0,1)\n",
" # if random_num > greater than epsilon --> exploitation\n",
" if random_num > epsilon:\n",
" # Take the action with the highest value given a state\n",
" # np.argmax can be useful here\n",
" action = greedy_policy(Qtable, state)\n",

6
units/en/unit2/hands-on.mdx
View File

@@ -388,9 +388,9 @@ def epsilon_greedy_policy(Qtable, state, epsilon):
```python
def epsilon_greedy_policy(Qtable, state, epsilon):
# Randomly generate a number between 0 and 1
random_int = random.uniform(0, 1)
# if random_int > greater than epsilon --> exploitation
if random_int > epsilon:
random_num = random.uniform(0, 1)
# if random_num > greater than epsilon --> exploitation
if random_num > epsilon:
# Take the action with the highest value given a state
# np.argmax can be useful here
action = greedy_policy(Qtable, state)