-
Hello, author.
I would like to ask about the reinforcement learning phase in explorer.py. After obtaining the entire process's state and reward, is the value predicted using the reward and the weight…
-
-
CI test **linux://rllib:learning_tests_multi_agent_pendulum_sac_multi_gpu** is consistently_failing. Recent failures:
- https://buildkite.com/ray-project/postmerge/builds/5994#01918161-64d5-42a6-ad4…
-
## 一言でいうと
最適なData Augmentationを探索する研究。画像の切断や反転・回転といった16の操作について、操作のパラメーター(回転の度合いや輝度など)、適用確率を離散化(それぞれ10、11)。2操作がワンセットで、それを5つ束ねたものが最終的な処理になり、これを強化学習で探索する(探索空間は3溝ほどにも及ぶ)。
### 論文リンク
https://arxiv.…
-
## Description
Most commands contain two or three words which makes it difficult and time-consuming for the user to type.
The use of hyphens also make the commands harder to type.
This goes agains…
-
CI test **linux://rllib:learning_tests_cartpole_dqn_multi_gpu** is consistently_failing. Recent failures:
- https://buildkite.com/ray-project/postmerge/builds/5932#01916ee4-1a09-4b7f-9a87-b19a6d6e3e…
-
### Feature Request
| Q | A
|------------ | ------
| New Feature | yes
| RFC | yes/no
| BC Break | yes/no
#### Summary
Requests are blocked between 2 hosts becaus…
-
https://arxiv.org/abs/1611.01626
-
I would like to ask about the upper and lower bounds of the obs space in `BaseRLAviary.py`, I. noticed that the bounds are - and + infinity, does not that make the state space very huge to be explored…
-
CI test **linux://rllib:learning_tests_multi_agent_cartpole_appo_gpu** is flaky. Recent failures:
- https://buildkite.com/ray-project/postmerge/builds/5169#01905ba9-2c2c-4ff0-ba8e-c17a10a43739
- ht…