Spaces:

ARKAISW
/

QuantHive

Running

App Files Files Community

QuantHive / training

77.8 kB

Ctrl+K

Ctrl+K

1 contributor

History: 5 commits

ARKAISW's picture

Semantic observation prompts — rich text replaces raw floats (judge feedback #1)

213c699 about 1 month ago

__init__.py

110 Bytes
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
benchmark.py

3.59 kB
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
config.py

1.97 kB
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
evaluate_live.py

7.15 kB
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
grpo_verifiers_multiagent.py

4.21 kB
Update training notebook and verifiers about 2 months ago
plot_multiagent.py

7.51 kB
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
prompt_utils.py

10.6 kB
Semantic observation prompts — rich text replaces raw floats (judge feedback #1) about 1 month ago
train.py

10.1 kB
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
train_cpu.py

3.54 kB
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
train_grpo.py

10.5 kB
Hackathon Final Submission: PettingZoo multi-agent arch, GRPO training, docs about 2 months ago
train_grpo_multiagent.py

6.88 kB
Update training notebook and verifiers about 2 months ago
train_multi_agent.py

11.7 kB
Update latest changes about 1 month ago