72a1d9d426
Itaicaspi/episode reset refactoring ( #105 )
...
* reordering of the episode reset operation and allowing to store episodes only when they are terminated
* reordering of the episode reset operation and allowing to store episodes only when they are terminated
* revert tensorflow-gpu to 1.9.0 + bug fix in should_train()
* tests readme file and refactoring of policy optimization agent train function
* Update README.md
* Update README.md
* additional policy optimization train function simplifications
* Updated the traces after the reordering of the environment reset
* docker and jenkins files
* updated the traces to the ones from within the docker container
* updated traces and added control suite to the docker
* updated jenkins file with the intel proxy + updated doom basic a3c test params
* updated line breaks in jenkins file
* added a missing line break in jenkins file
* refining trace tests ignored presets + adding a configurable beta entropy value
* switch the order of trace and golden tests in jenkins + fix golden tests processes not killed issue
* updated benchmarks for dueling ddqn breakout and pong
* allowing dynamic updates to the loss weights + bug fix in episode.update_returns
* remove docker and jenkins file
2018-09-04 15:07:54 +03:00
7086492127
parallel trace tests fix
2018-09-03 20:47:10 +03:00
2c62a40466
bug fix in dueling network + revert to TF 1.6 for CPU due to requirements compatibility issues
2018-09-02 13:38:16 +03:00
3a399d1361
Tensorflow 1.10 and python 3.6 ( #104 )
...
* updating setup.py to install tensorflow 1.10 both on cpu and on gpu
* allow python 3.6
2018-09-02 10:12:00 +03:00
5aca3a5ed1
Update README.md
2018-08-30 23:33:44 +03:00
55c3034f4d
Update README.md
2018-08-30 23:25:10 +03:00
e5526b98f8
Update README.md
2018-08-30 22:58:37 +03:00
d862a3be83
rainbow dqn hyper-parameter updates
2018-08-30 20:41:38 +03:00
07db625987
Running trace tests in parallel + other small fixes
2018-08-30 19:35:10 +03:00
ebe574e463
add missing hidden layer in rainbow_q_head
2018-08-30 19:34:27 +03:00
ea294de7fd
adding dueling support for rainbow dqn (now only missing n-step)
2018-08-30 18:15:59 +03:00
d2623c0eee
bug-fix in dueling dqn
2018-08-30 18:14:53 +03:00
bbe7ac3338
Rainbow DQN agent (WIP - still missing dueling and n-step) + adding support for Prioritized ER for C51
2018-08-30 18:14:53 +03:00
fd2f4b0852
bug fix in HRL HER memory + some small improvements
2018-08-29 14:36:18 +03:00
1aa2ab0590
parameter noise exploration - using Noisy Nets
2018-08-27 18:19:01 +03:00
658b437079
removing datasets + imports optimization
2018-08-27 10:54:11 +03:00
d826382b11
removing test from Doom_Health_Supreme_DFP + relaxing time limit on reward tests
2018-08-26 18:42:41 +03:00
2021490caa
small adjustment to golden tests + fixes for Doom_Health_DFP and Doom_Health_Supreme_DFP
2018-08-26 18:42:41 +03:00
3fd0bf4f0f
Update README.md
2018-08-26 12:09:46 +03:00
9bb7bd2e9c
bug-fix in local_batch_run_coach and rename to run_multiple_seeds
2018-08-23 14:39:11 +03:00
a4471389a4
brightened starcraft.gif
2018-08-20 13:50:09 +03:00
904570000a
Update README.md
2018-08-20 12:04:29 +03:00
5e275e9795
update starcraft gif
2018-08-20 11:49:19 +03:00
3abb6cd415
Trace tests update
2018-08-20 13:01:30 +03:00
c1f428666e
bug-fix for checkpointing for single-worker algorithms
2018-08-19 20:17:15 +03:00
9f599f38cf
Update README.md
2018-08-19 13:09:06 +03:00
c5165cd7d6
benchmarks and pip package updates
2018-08-19 14:23:20 +03:00
23d2945bf8
Update README.md
2018-08-19 11:02:45 +03:00
0be4a42701
updates needed for the pip package
2018-08-19 10:39:03 +03:00
e2e8143b94
additional benchmarks for dqn and a3c
2018-08-18 15:21:50 +03:00
2d5688c737
additional benchmarks for a3c and dqn
2018-08-16 20:01:35 +03:00
1de04d6fee
updated gifs in README + fix for multiworker crashes + improved Atari DQN and Dueling DDQN presets
2018-08-16 18:23:32 +03:00
8f99409387
updating algorithms.png for README
2018-08-16 16:46:26 +03:00
ab5a81c7ee
fix for dumping movies, without rendering, for pendulum_with_goals
2018-08-14 18:13:44 +03:00
e783157b15
Update README.md
2018-08-14 16:16:41 +03:00
824fdeee59
Update README with new coach aliases
2018-08-14 14:36:41 +03:00
7a76d63da4
Update README.md
2018-08-13 17:19:47 +03:00
19ca5c24b1
pre-release 0.10.0
2018-08-13 17:11:34 +03:00
d44c329bb8
Update README.md
2018-06-25 17:46:01 +03:00
cfd4fe0faf
Update README.md
2018-06-25 17:43:15 +03:00
2807c29f27
fix for measurements in the initial state (fix for DFP)
2018-05-29 16:47:38 +03:00
7725dabc86
checkpoints bug fix
2018-05-26 17:49:13 +03:00
462c6e314b
bug fix in nec checkpoint saving
2018-05-24 15:15:33 +03:00
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
6c0b59b4de
constraining gym installation to version 0.9.4
2018-05-22 11:01:58 +03:00
a57b7004a8
updating dashboard
2018-05-09 09:26:15 +03:00
dafdb05a7c
bug fixes for clippedppo and checkpoints
2018-04-30 15:13:29 +03:00
f31159aad6
bug fixes for carla environment ( #93 )
2018-04-23 11:13:24 +03:00
52eb159f69
multiple bug fixes in dealing with measurements + CartPole_DFP preset ( #92 )
2018-04-23 10:44:46 +03:00
5d5562bf62
moving the docs to github
2018-04-23 09:14:20 +03:00
Itai Caspi