dr_domi/udlbook
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: correct terminal state

Browse Source
This commit is contained in:
jalaneunos
2026-01-05 10:47:35 +08:00
parent 60d50aa9d2
commit 080bdd319d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Notebooks/Chap19/19_3_Monte_Carlo_Methods.ipynb
View File

@@ -437,7 +437,7 @@
" new_state = np.random.choice(a=np.arange(0,transition_probabilities_given_action.shape[0]),p = transition_probabilities_given_action[:,state,action])\n", " new_state = np.random.choice(a=np.arange(0,transition_probabilities_given_action.shape[0]),p = transition_probabilities_given_action[:,state,action])\n",
" # Return the reward\n", " # Return the reward\n",
" reward = reward_structure[new_state]\n", " reward = reward_structure[new_state]\n",
" is_terminal = new_state in [terminal_states]\n", " is_terminal = new_state in terminal_states\n",
"\n", "\n",
" return new_state, reward, action, is_terminal" " return new_state, reward, action, is_terminal"
] ]