Skip to content

Commit edcba6b

Browse files
author
Sanyam Kapoor
committed
Fix step and reset NotImplementedError
1 parent 5334a6f commit edcba6b

File tree

2 files changed

+34
-145
lines changed

2 files changed

+34
-145
lines changed

‎MC/Blackjack Playground.ipynb‎

Lines changed: 27 additions & 144 deletions
Original file line numberDiff line numberDiff line change
@@ -2,10 +2,8 @@
22
"cells": [
33
{
44
"cell_type": "code",
5-
"execution_count": 419,
6-
"metadata": {
7-
"collapsed": true
8-
},
5+
"execution_count": 1,
6+
"metadata": {},
97
"outputs": [],
108
"source": [
119
"import numpy as np\n",
@@ -17,7 +15,7 @@
1715
},
1816
{
1917
"cell_type": "code",
20-
"execution_count": 420,
18+
"execution_count": 2,
2119
"metadata": {},
2220
"outputs": [],
2321
"source": [
@@ -26,151 +24,29 @@
2624
},
2725
{
2826
"cell_type": "code",
29-
"execution_count": 422,
27+
"execution_count": 3,
3028
"metadata": {},
3129
"outputs": [
3230
{
3331
"name": "stdout",
3432
"output_type": "stream",
3533
"text": [
36-
"Player Score: 17 (Usable Ace: False), Dealer Score: 10\n",
37-
"Taking action: Hit\n",
38-
"Player Score: 18 (Usable Ace: False), Dealer Score: 10\n",
39-
"Taking action: Hit\n",
40-
"Player Score: 28 (Usable Ace: False), Dealer Score: 10\n",
41-
"Game end. Reward: -1.0\n",
42-
"\n",
43-
"Player Score: 6 (Usable Ace: False), Dealer Score: 9\n",
44-
"Taking action: Hit\n",
45-
"Player Score: 16 (Usable Ace: False), Dealer Score: 9\n",
46-
"Taking action: Hit\n",
47-
"Player Score: 26 (Usable Ace: False), Dealer Score: 9\n",
48-
"Game end. Reward: -1.0\n",
49-
"\n",
50-
"Player Score: 12 (Usable Ace: False), Dealer Score: 6\n",
51-
"Taking action: Hit\n",
52-
"Player Score: 21 (Usable Ace: False), Dealer Score: 6\n",
53-
"Taking action: Stick\n",
54-
"Player Score: 21 (Usable Ace: False), Dealer Score: 6\n",
55-
"Game end. Reward: 1.0\n",
56-
"\n",
57-
"Player Score: 17 (Usable Ace: True), Dealer Score: 8\n",
58-
"Taking action: Hit\n",
59-
"Player Score: 17 (Usable Ace: False), Dealer Score: 8\n",
60-
"Taking action: Hit\n",
61-
"Player Score: 22 (Usable Ace: False), Dealer Score: 8\n",
62-
"Game end. Reward: -1.0\n",
63-
"\n",
6434
"Player Score: 17 (Usable Ace: False), Dealer Score: 8\n",
65-
"Taking action: Hit\n",
66-
"Player Score: 27 (Usable Ace: False), Dealer Score: 8\n",
67-
"Game end. Reward: -1.0\n",
68-
"\n",
69-
"Player Score: 16 (Usable Ace: False), Dealer Score: 10\n",
70-
"Taking action: Hit\n",
71-
"Player Score: 19 (Usable Ace: False), Dealer Score: 10\n",
72-
"Taking action: Hit\n",
73-
"Player Score: 28 (Usable Ace: False), Dealer Score: 10\n",
74-
"Game end. Reward: -1.0\n",
75-
"\n",
76-
"Player Score: 13 (Usable Ace: False), Dealer Score: 7\n",
77-
"Taking action: Hit\n",
78-
"Player Score: 14 (Usable Ace: False), Dealer Score: 7\n",
79-
"Taking action: Hit\n",
80-
"Player Score: 24 (Usable Ace: False), Dealer Score: 7\n",
81-
"Game end. Reward: -1.0\n",
82-
"\n",
83-
"Player Score: 17 (Usable Ace: False), Dealer Score: 5\n",
84-
"Taking action: Hit\n",
85-
"Player Score: 25 (Usable Ace: False), Dealer Score: 5\n",
86-
"Game end. Reward: -1.0\n",
87-
"\n",
88-
"Player Score: 20 (Usable Ace: False), Dealer Score: 5\n",
89-
"Taking action: Stick\n",
90-
"Player Score: 20 (Usable Ace: False), Dealer Score: 5\n",
91-
"Game end. Reward: 1.0\n",
92-
"\n",
93-
"Player Score: 12 (Usable Ace: True), Dealer Score: 10\n",
94-
"Taking action: Hit\n",
95-
"Player Score: 20 (Usable Ace: True), Dealer Score: 10\n",
96-
"Taking action: Stick\n",
97-
"Player Score: 20 (Usable Ace: True), Dealer Score: 10\n",
98-
"Game end. Reward: 0.0\n",
99-
"\n",
100-
"Player Score: 12 (Usable Ace: False), Dealer Score: 10\n",
101-
"Taking action: Hit\n",
102-
"Player Score: 19 (Usable Ace: False), Dealer Score: 10\n",
103-
"Taking action: Hit\n",
104-
"Player Score: 24 (Usable Ace: False), Dealer Score: 10\n",
105-
"Game end. Reward: -1.0\n",
106-
"\n",
107-
"Player Score: 19 (Usable Ace: False), Dealer Score: 4\n",
108-
"Taking action: Hit\n",
109-
"Player Score: 22 (Usable Ace: False), Dealer Score: 4\n",
110-
"Game end. Reward: -1.0\n",
111-
"\n",
112-
"Player Score: 16 (Usable Ace: False), Dealer Score: 10\n",
113-
"Taking action: Hit\n",
114-
"Player Score: 20 (Usable Ace: False), Dealer Score: 10\n",
115-
"Taking action: Stick\n",
116-
"Player Score: 20 (Usable Ace: False), Dealer Score: 10\n",
117-
"Game end. Reward: 0.0\n",
118-
"\n",
119-
"Player Score: 4 (Usable Ace: False), Dealer Score: 3\n",
120-
"Taking action: Hit\n",
121-
"Player Score: 14 (Usable Ace: False), Dealer Score: 3\n",
122-
"Taking action: Hit\n",
123-
"Player Score: 24 (Usable Ace: False), Dealer Score: 3\n",
124-
"Game end. Reward: -1.0\n",
125-
"\n",
126-
"Player Score: 21 (Usable Ace: True), Dealer Score: 10\n",
127-
"Taking action: Stick\n",
128-
"Player Score: 21 (Usable Ace: True), Dealer Score: 10\n",
129-
"Game end. Reward: 1.0\n",
130-
"\n",
131-
"Player Score: 16 (Usable Ace: True), Dealer Score: 10\n",
132-
"Taking action: Hit\n",
133-
"Player Score: 12 (Usable Ace: False), Dealer Score: 10\n",
134-
"Taking action: Hit\n",
135-
"Player Score: 20 (Usable Ace: False), Dealer Score: 10\n",
136-
"Taking action: Stick\n",
137-
"Player Score: 20 (Usable Ace: False), Dealer Score: 10\n",
138-
"Game end. Reward: 1.0\n",
139-
"\n",
140-
"Player Score: 9 (Usable Ace: False), Dealer Score: 10\n",
141-
"Taking action: Hit\n",
142-
"Player Score: 19 (Usable Ace: False), Dealer Score: 10\n",
143-
"Taking action: Hit\n",
144-
"Player Score: 26 (Usable Ace: False), Dealer Score: 10\n",
145-
"Game end. Reward: -1.0\n",
146-
"\n",
147-
"Player Score: 12 (Usable Ace: False), Dealer Score: 5\n",
148-
"Taking action: Hit\n",
149-
"Player Score: 15 (Usable Ace: False), Dealer Score: 5\n",
150-
"Taking action: Hit\n",
151-
"Player Score: 21 (Usable Ace: False), Dealer Score: 5\n",
152-
"Taking action: Stick\n",
153-
"Player Score: 21 (Usable Ace: False), Dealer Score: 5\n",
154-
"Game end. Reward: 1.0\n",
155-
"\n",
156-
"Player Score: 11 (Usable Ace: False), Dealer Score: 9\n",
157-
"Taking action: Hit\n",
158-
"Player Score: 13 (Usable Ace: False), Dealer Score: 9\n",
159-
"Taking action: Hit\n",
160-
"Player Score: 17 (Usable Ace: False), Dealer Score: 9\n",
161-
"Taking action: Hit\n",
162-
"Player Score: 19 (Usable Ace: False), Dealer Score: 9\n",
163-
"Taking action: Hit\n",
164-
"Player Score: 29 (Usable Ace: False), Dealer Score: 9\n",
165-
"Game end. Reward: -1.0\n",
166-
"\n",
167-
"Player Score: 14 (Usable Ace: False), Dealer Score: 7\n",
168-
"Taking action: Hit\n",
169-
"Player Score: 19 (Usable Ace: False), Dealer Score: 7\n",
170-
"Taking action: Hit\n",
171-
"Player Score: 29 (Usable Ace: False), Dealer Score: 7\n",
172-
"Game end. Reward: -1.0\n",
173-
"\n"
35+
"Taking action: Hit\n"
36+
]
37+
},
38+
{
39+
"ename": "RecursionError",
40+
"evalue": "maximum recursion depth exceeded",
41+
"output_type": "error",
42+
"traceback": [
43+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
44+
"\u001b[0;31mRecursionError\u001b[0m Traceback (most recent call last)",
45+
"\u001b[0;32m<ipython-input-3-e78e3f41e925>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[0maction\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstrategy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobservation\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Taking action: {}\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\"Stick\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"Hit\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0maction\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 17\u001b[0;31m \u001b[0mobservation\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreward\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0menv\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 18\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[0mprint_observation\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobservation\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
46+
"\u001b[0;32m~/Workspace/src/github.com/dennybritz/reinforcement-learning/lib/envs/blackjack.py\u001b[0m in \u001b[0;36mstep\u001b[0;34m(self, action)\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 85\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 86\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 87\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 88\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_seed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mseed\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
47+
"... last 1 frames repeated, from the frame below ...\n",
48+
"\u001b[0;32m~/Workspace/src/github.com/dennybritz/reinforcement-learning/lib/envs/blackjack.py\u001b[0m in \u001b[0;36mstep\u001b[0;34m(self, action)\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 85\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 86\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0maction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 87\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 88\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_seed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mseed\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
49+
"\u001b[0;31mRecursionError\u001b[0m: maximum recursion depth exceeded"
17450
]
17551
}
17652
],
@@ -197,6 +73,13 @@
19773
" print(\"Game end. Reward: {}\\n\".format(float(reward)))\n",
19874
" break"
19975
]
76+
},
77+
{
78+
"cell_type": "code",
79+
"execution_count": null,
80+
"metadata": {},
81+
"outputs": [],
82+
"source": []
20083
}
20184
],
20285
"metadata": {
@@ -215,7 +98,7 @@
21598
"name": "python",
21699
"nbconvert_exporter": "python",
217100
"pygments_lexer": "ipython3",
218-
"version": "3.5.2"
101+
"version": "3.6.4"
219102
}
220103
},
221104
"nbformat": 4,

‎lib/envs/blackjack.py‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,6 +79,12 @@ def __init__(self, natural=False):
7979
self._reset() # Number of
8080
self.nA = 2
8181

82+
def reset(self):
83+
return self._reset()
84+
85+
def step(self, action):
86+
return self._step(action)
87+
8288
def _seed(self, seed=None):
8389
self.np_random, seed = seeding.np_random(seed)
8490
return [seed]
@@ -113,4 +119,4 @@ def _reset(self):
113119
while sum_hand(self.player) < 12:
114120
self.player.append(draw_card(self.np_random))
115121

116-
return self._get_obs()
122+
return self._get_obs()

0 commit comments

Comments
 (0)