gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 11:10:20 +01:00
Code Issues Projects Releases Wiki Activity
108 Commits 4 Branches 2 Tags
d302168c8c817e5d4f4a59d9f5dfe283a4150cb1
Commit Graph

14 Commits

Author SHA1 Message Date
Itai Caspi
d302168c8c Parallel agents fixes (#95) 
* Parallel agents related bug fixes: checkpoint restore, tensorboard integration.
Adding narrow networks support.
Reference code for unlimited number of checkpoints
 2018-05-24 14:24:19 +03:00
Itai Caspi
a7206ed702 Multiple improvements and bug fixes (#66) 
* Multiple improvements and bug fixes:

    * Using lazy stacking to save on memory when using a replay buffer
    * Remove step counting for evaluation episodes
    * Reset game between heatup and training
    * Major bug fixes in NEC (is reproducing the paper results for pong now)
    * Image input rescaling to 0-1 is now optional
    * Change the terminal title to be the experiment name
    * Observation cropping for atari is now optional
    * Added random number of noop actions for gym to match the dqn paper
    * Fixed a bug where the evaluation episodes won't start with the max possible ale lives
    * Added a script for plotting the results of an experiment over all the atari games
 2018-02-26 12:29:07 +02:00
Zach Dwiel
98f57a0d87 fix ddpg 2018-02-21 10:05:57 -05:00
Zach Dwiel
ee6e0bdc3b fix keep_dims -> keepdims 2018-02-21 10:05:57 -05:00
Zach Dwiel
85afb86893 temp commit 2018-02-21 10:05:57 -05:00
Gal Leibovich
7c8962c991 adding support in tensorboard (#52) 
* bug-fix in architecture.py where additional fetches would acquire more entries than it should
* change in run_test to allow ignoring some test(s)
 2018-02-05 15:21:49 +02:00
Zach Dwiel
6c79a442f2 update nec and value optimization agents to work with recurrent middleware 2018-01-05 20:16:51 -05:00
Itai Caspi
11faf19649 QR-DQN bug fix and imporvements (#30) 
* bug fix - QR-DQN using error instead of abs-error in the quantile huber loss

* improvement - QR-DQN sorting the quantile only once instead of batch_size times

* new feature - adding the Breakout QRDQN preset (verified to achieve good results)
 2017-11-29 14:01:59 +02:00
galleibo-intel
3c330768f0 Fix for NEC not saving the DND when saving a model 2017-11-09 19:13:23 +02:00
Itai Caspi
a8bce9828c new feature - implementation of Quantile Regression DQN (https://arxiv.org/pdf/1710.10044v1.pdf) 
API change - Distributional DQN renamed to Categorical DQN
 2017-11-01 15:09:07 +02:00
Itai Caspi
913ab75e8a bug fix - preventing crashes when the probability of one of the actions is 0 in the policy head 2017-10-31 10:51:48 +02:00
Itai Caspi
1918f16079 imporved API for getting / setting variables within the graph 2017-10-31 10:51:48 +02:00
cxx
f43c951c2d Unify base class using new-style (object). 2017-10-26 12:33:09 +03:00
Gal Leibovich
1d4c3455e7 coach v0.8.0 2017-10-19 13:10:15 +03:00