Spaces:

shriom23
/

MedFlow-OpenEnv

Sleeping

App Files Files Community

MedFlow-OpenEnv

Commit History

Jun 4

09:00
Doctor & Patient list updated

shriom17

77f5df3
08:40
UI updated to "Simulation Metrics" from "Episode Summary" to better reflect the content being displayed.

shriom17

45cf6a2

Jun 2

09:52
README updated

shriom17

069bf2a
09:50
Updated UI

shriom17

3d5fe67
07:51
Training Completed - Training of the Q-learning agent has been completed successfully. The training process has generated various evaluation outputs, including loss curves, reward curves, and summary files for both the training and TRL (Training Reinforcement Learning) phases.

shriom17

58e797b

Apr 26

10:11
readme polished

shriom17

13cd3d0
09:35
readme fixed

shriom17

6aa63e9
09:26
demo link added to readme

shriom17

5dde4cd
08:10
notebook added

shriom17

713e6db
07:43
outputs

shriom17

7fcf2a0
05:35
fixed

shriom17

262f1e9
05:32
fixed

shriom17

731019c
05:29
readme polished

shriom17

39c6dc9
05:28
hf template updated

shriom17

9aba43f
05:26
readme polished

shriom17

3b0fac8
04:46
openenv version updated

shriom17

380e5be
04:22
New training notebook with Q-learning implementation and updated LLM prompting. Updated openenv.yaml with new artifact paths and links. Updated UI to show final score in episode summary.

shriom17

7bf75d1
04:22
Created using Colab

SHRIOM

a763a46
04:10
Created using Colab

SHRIOM

f115857
01:24
UI polished

shriom17

535efd1

Apr 25

14:21
naming issue fixed

shriom17

b123f6f
13:14
ui polished

shriom17

eeb795d
13:06
Fix serialization; add /llm-step heuristic fallback and UI graph polish

shriom17

109978b
09:54
Learning Ui improvements for reward graph and curve, adding a subtle animation to the reward curve fill, and enhancing the overall visual appeal of the reward graph section.

shriom17

3b45036
09:32
UI polished

shriom17

351dfb7
08:05
UI polished

shriom17

7d7c923
07:19
Qlearning done

shriom17

ec8b84f
06:57
Created using Colab

SHRIOM

7d6d2f8
03:58
Created using Colab

SHRIOM

54296ad
03:56
Created using Colab

SHRIOM

e238de4
03:02
real logic added

shriom17

e9ca231

Apr 23

14:17
Training updated

shriom17

9c9d90f

Apr 22

13:40
Created using Colab

SHRIOM

8bb38b7
04:26
greedy logic added

shriom17

f0b29e9

Apr 21

16:12
env_client added

shriom17

aa51a2b
16:08
collab issue fixed

shriom17

2fca932
15:07
Training added

shriom17

b0bf770

Apr 9

18:15
Include templates in Docker image for HF Space

shriom17

445c864
17:13
UI polished

shriom17

430b523
16:51
UI polished

shriom17

02a8abc
07:09
Fix UI fallback when template file is missing

shriom17

1e6e58a
07:04
Rebuild clean history without binary assets

shriom17

0d2e609

Commit History

Jun 4

Doctor & Patient list updated

UI updated to "Simulation Metrics" from "Episode Summary" to better reflect the content being displayed.

Jun 2

README updated

Updated UI

Training Completed - Training of the Q-learning agent has been completed successfully. The training process has generated various evaluation outputs, including loss curves, reward curves, and summary files for both the training and TRL (Training Reinforcement Learning) phases.

Apr 26

readme polished

readme fixed

demo link added to readme

notebook added

outputs

fixed

fixed

readme polished

hf template updated

readme polished

openenv version updated

New training notebook with Q-learning implementation and updated LLM prompting. Updated openenv.yaml with new artifact paths and links. Updated UI to show final score in episode summary.

Created using Colab

Created using Colab

UI polished

Apr 25

naming issue fixed

ui polished

Fix serialization; add /llm-step heuristic fallback and UI graph polish

Learning Ui improvements for reward graph and curve, adding a subtle animation to the reward curve fill, and enhancing the overall visual appeal of the reward graph section.

UI polished

UI polished

Qlearning done

Created using Colab

Created using Colab

Created using Colab

real logic added

Apr 23

Training updated

Apr 22

Created using Colab

greedy logic added

Apr 21

env_client added

collab issue fixed

Training added

Apr 9

Include templates in Docker image for HF Space

UI polished

UI polished

Fix UI fallback when template file is missing

Rebuild clean history without binary assets