Chris McCarthy
8edb26a65c
Merge remote-tracking branch 'origin/dev' into 1566-configure-episode-steps-learn-eval
...
# Conflicts:
# src/primaite/agents/rllib.py
2023-07-07 14:34:20 +01:00
SunilSamra
79d98e977b
1566 - added test file and edited configs to include types of num steps and modifed agents to use correct step and episode counts
2023-07-07 14:13:47 +01:00
Czar Echavez
76997f403e
Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test
2023-07-06 22:22:37 +01:00
Czar Echavez
bb9bfc50a5
#1386 : remove setting of global seed + running pre-commit checks
2023-07-06 12:10:26 +01:00
Chris McCarthy
a35c363345
#1386 - Updated tests in test_seeding_and_deterministic_session.py to use TempPrimaiteSession.
...
- Added test_seeded_learning test and test_deterministic_evaluation test.
- Passed config values seed and deterministic to ppo agent
- Dropped deterministic override in evaluate functions
- TempPrimaiteSession now writes files to a UUID folder rather than datetime
- Added seed to Ray RLlib agent setup in rllib.py
- Added seed to SB3 agent setup in sb3.py
2023-07-06 11:35:44 +01:00
Chris McCarthy
f92d2fb65d
temp
2023-07-06 10:07:54 +01:00
Czar Echavez
b0c83d7148
#1386 : fix saving of agent
2023-07-05 11:41:18 +01:00
Czar Echavez
818d64f330
#1386 : fix bug with agent zip file not being saved after run
2023-07-04 16:30:31 +01:00
Chris McCarthy
06d5004695
#917 - Dropped VerboseLevel in enums.py and changed OutputVerboseLevel to SB3OutputVerboseLevel
2023-06-30 17:09:50 +01:00
Chris McCarthy
e11fd2ced4
#917 - Fixed the RLlib integration
...
- Dropped support for overriding the num_episodes and num_steps at the agent level. It's just not needed and will add complexity when overriding and writing output files.
2023-06-30 16:52:57 +01:00
Chris McCarthy
7b1f889415
#917 - Integrated the PrimaiteSession into all tests.
...
- Ran a full pre-commit hook and thus encountered tons of fixes required
2023-06-30 09:08:13 +01:00
Chris McCarthy
b6d93ad33f
#917 - Began the process of reloading existing agents into the session
2023-06-28 19:54:00 +01:00
Chris McCarthy
4866722911
#917 - Overhauled transaction and mean reward writing.
...
- Separated out learning outputs from evaluation outputs
2023-06-28 16:34:00 +01:00
Chris McCarthy
a9ebfd7917
#917 - Synced with dev and added better logging
2023-06-28 12:01:01 +01:00
Chris McCarthy
dce6fe55ee
#917 - Got things working'ish
2023-06-20 22:29:46 +01:00
Chris McCarthy
7b0f47d6f8
#917 -Finished integrating all agents to either train (policy agents) or evaluate (hard-coded agents). Still some fixing up to do, tidying up, loading etc. also docs. But this is all now working.
2023-06-20 16:06:55 +01:00
Chris McCarthy
10c94954a5
#917 - Almost there. All output files being writen for SB3/RLLIB PPO & A2C. Just need to bring in the hardcoded agents then update the testa and docs.
2023-06-19 21:53:25 +01:00
Chris McCarthy
3670f16766
#917 - Integrated both SB3 and RLlib agents into PrimaiteSession
2023-06-19 20:27:08 +01:00
Chris McCarthy
c09874edbe
#917 - Got RLlib fully training in PrimAITE. Started integrating the the other agents into the Session class
2023-06-18 22:40:56 +01:00
Chris McCarthy
31eb36c75a
#917 - started working on the Agent abstract classes and sub-classes
2023-06-15 09:48:44 +01:00
Chris McCarthy
40686031e6
temp commit
2023-06-13 09:42:54 +01:00
