Downloads · 30 days
0
sokoban_adaptive_mixed_forward_rl_step10
novastar111/sokoban_adaptive_mixed_forward_rl_step10
sokoban_adaptive_mixed_forward_rl_step10 is a reinforcement learning model from novastar111. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
BAGEL-7B-MoT Sokoban checkpoint after 10 IMP-agent RL steps.
Access
Public
Updated Aug 19, 2026
Repo size
29.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29.2 GB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026
- SHA
- 25906710
Model card
From the Hugging Face model README
sokoban_adaptive_mixed_forward_rl_step10
BAGEL-7B-MoT Sokoban checkpoint after 10 IMP-agent RL steps.
- arm: mixed-forward
- initialization:
novastar111/sokoban_adaptive_mixed_forward_sft3k - training set: 2,000 mixed 3-box Sokoban boards (certified-deadlock and trivial strata)
- optimization: global batch 16, 8 rollouts per prompt, learning rate 2e-6
- reward: stop-required environment success with a -0.1 malformed-output penalty
- weights: converted BF16 EMA safetensors; optimizer/training state is not included
This repository is one point in the complete 10-step release ladder from RL10 through RL200.
Evaluation uses Sokoban-v8 q95/perseg, full model rollout, move-only actions, and stop-required
success. Load with the public BAGEL-7B-MoT base/config and use ema.safetensors as the model delta.
- Task
- Reinforcement Learning
- License
- cc-by-nc-4.0
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026