Views
No views yet
| Env | Latents seen during training |
|---|---|
| hangman | vowel_count_4, ending_ABLE |
| wordladder | hub_word_3letter, hub_word_4letter, order_outside_in |
| secretary | inverse_order, fixed_position_2 |
| number_guessing | set_of_3, range_100 |
| 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) | 1 |
| Reward Φ | Σᵢ Gᵢ (cumulative) |
| Epochs | 20 |
| Max generation length | 64 |
| Sampling (train) | T=0.8, top-p=0.95 |
| Seed | 263 |