Commit 07dcad5f authored by Ladislav Hlatky's avatar Ladislav Hlatky
Browse files

Upload New File

parent a3028891
testing_id: 1593553526
lander-doubleDQN-v13
number of tests: 10
NUMBER_OF_EPISODES_MAX: 600
NUMBER_OF_STEPS_MAX: 1000
LEARNING_RATE: 0.001000
GAMMA: 0.990000
EPSILON_MAX: 1.000000
EPSILON_MIN: 0.010000
EPSILON_DECAY: 0.995000
MEMORY_SIZE: 500000
BATCH_SIZE: 64
LAST_100_REWARD_GOAL: 200.000000
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 512) 4608
_________________________________________________________________
dense_2 (Dense) (None, 256) 131328
_________________________________________________________________
dense_3 (Dense) (None, 4) 1028
=================================================================
Total params: 136,964
Trainable params: 136,964
Non-trainable params: 0
_________________________________________________________________
Test 0
duration:
1549
episodes to LAST_100_REWARD_GOAL
476
Test 1
duration:
1631
episodes to LAST_100_REWARD_GOAL
0
Test 2
duration:
1190
episodes to LAST_100_REWARD_GOAL
0
Test 3
duration:
1086
episodes to LAST_100_REWARD_GOAL
0
Test 4
duration:
1072
episodes to LAST_100_REWARD_GOAL
0
Test 5
duration:
969
episodes to LAST_100_REWARD_GOAL
0
Test 6
duration:
1002
episodes to LAST_100_REWARD_GOAL
0
Test 7
duration:
970
episodes to LAST_100_REWARD_GOAL
0
Test 8
duration:
1307
episodes to LAST_100_REWARD_GOAL
0
Test 9
duration:
1143
episodes to LAST_100_REWARD_GOAL
0
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment