CUN-bjy/gym-ddpg-keras
Keras Implementation of DDPG(Deep Deterministic Policy Gradient) with PER(Prioritized Experience Replay) option on OpenAI gym framework
PythonGPL-3.0
Issues
- 0
hyperparameter setting on config file
#25 opened by CUN-bjy - 2
DDPG w/ :RoboschoolHopper-v1
#24 opened by CUN-bjy - 2
- 3
cartpole learning(discrete)
#16 opened by CUN-bjy - 1
train by cuda
#5 opened by CUN-bjy - 1
UserWarning: Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.
#19 opened by CUN-bjy - 0
- 1
IS weight on PER
#17 opened by CUN-bjy - 0
learning status reporting for analysis
#7 opened by CUN-bjy - 0
memorize and replay with PER
#12 opened by CUN-bjy - 0
load pre-trained weights
#11 opened by CUN-bjy - 6
look like not being trained
#4 opened by CUN-bjy - 1
support various model
#10 opened by CUN-bjy - 1
easy environment making
#8 opened by CUN-bjy - 0
- 1
Simulation is too slow
#3 opened by CUN-bjy - 3
5 out of the last 5 calls to <function Model.make_train_function.<locals>.train_function at 0x7f627418ac80> triggered tf.function retracing.
#1 opened by CUN-bjy