Commit 809988d
add chapter 18 and 19 for 4th edition (aimacode#1076)
* chapter 18 learning
* add chapter 19
* move init dataset in NN learner
* add adam optimizer, add nn learner
* remove cpt 19 for debug
* change while loop in games4e
* add chapter 19
* add sgd and adam optimizer
* add chpt19 deep nn
* add rnn
* add auto encoder
* add comments, correct tests
* add more comments, change algorithms according to orders of chapter sections
* add keras and numpy to requirements
* add tf as requirement
* add gc in test agent
* fix agent bugs for running test_agent and test_agent_4e together
* fix build error
* add chapter 21 and 22
* add chapter 12 and part of 13
* remove chapter 12 and 13, add test of rl
* modify rnn test
* fix build error
* Update utils4e.py1 parent 37110de commit 809988d
13 files changed
Lines changed: 2600 additions & 14 deletions
Large diffs are not rendered by default.
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
@@ -514,7 +514,7 @@ def add_thing(self, thing, location=(1, 1), exclude_duplicate_class_items=False) | |||
| 514 | 514 | def is_inbounds(self, location): | |
| 515 | 515 | """Checks to make sure that the location is inbounds (within walls if we have walls)""" | |
| 516 | 516 | x, y = location | |
| 517 | - return not (x < self.x_start or x >= self.x_end or y < self.y_start or y >= self.y_end) | ||
| 517 | + return not (x < self.x_start or x > self.x_end or y < self.y_start or y > self.y_end) | ||
| 518 | 518 | ||
| 519 | 519 | def random_location_inbounds(self, exclude=None): | |
| 520 | 520 | """Returns a random location that is inbounds (within walls if we have walls)""" | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
@@ -210,12 +210,12 @@ def backprop(n, utility): | |||
| 210 | 210 | ||
| 211 | 211 | root = MCT_Node(state=state) | |
| 212 | 212 | ||
| 213 | - while N > 0: | ||
| 213 | + for _ in range(N): | ||
| 214 | 214 | leaf = select(root) | |
| 215 | 215 | child = expand(leaf) | |
| 216 | 216 | result = simulate(game, child.state) | |
| 217 | 217 | backprop(child, result) | |
| 218 | - N -= 1 | ||
| 218 | + | ||
| 219 | 219 | max_state = max(root.children, key=lambda p: p.N) | |
| 220 | 220 | ||
| 221 | 221 | return root.children.get(max_state) | |
0 commit comments