base_model, license, library_name, pipeline_tag, language, tags

base_model	license	library_name	pipeline_tag	language	tags
Qwen/Qwen3-8B	apache-2.0	transformers	text-generation	en	qwen3 meta-rl in-context-learning grpo

LatentGym_Qwen3-8B_10episodes_MultiLatent_hangman

GRPO-fine-tuned Qwen3-8B for in-context meta-learning on hangman (3 latents, N=10). Part of the LatentGym testbed.

Environments & training latents

Env	Latents seen during training
hangman	vowel_count_4, has_double_letter, starts_with_S

Training hyperparameters

Base model	Qwen/Qwen3-8B
Algorithm	GRPO
Optimizer	AdamW (β₁=0.9, β₂=0.999)
Learning rate	5e-07
LR schedule	constant_with_warmup
Weight decay	0.01
Max grad norm	1.0
KL coefficient β	0.04
Clip range ε	0.2
Train batch (prompts)	32
Mini-batch	1
Rollouts per prompt	8
Episodes per trajectory (N)	10
Reward Φ	Σᵢ Gᵢ (cumulative)
Epochs	20
Max generation length	64
Sampling (train)	T=0.8, top-p=0.95
Seed	263