# ── Environments ──────────────────────────────────────────────────────
id_envs:
  - MiniHack-Room-Random-5x5-v0
  - MiniHack-Room-Random-15x15-v0
  - MiniHack-Corridor-R2-v0
  - MiniHack-MazeWalk-9x9-v0
ood_envs:
  - MiniHack-Room-Dark-15x15-v0
  - MiniHack-Corridor-R5-v0
  - MiniHack-MazeWalk-45x19-v0
crop_size: 9
map_h: 21
map_w: 79
action_dim: 12
mask_token: 12
pad_token: 13

# ── Model ─────────────────────────────────────────────────────────────
n_embd: 256
n_head: 4
n_layer: 4
n_global_tokens: 8
seq_len: 64
global_gate_init: -3.0
# Transformer dropout. 0.0 is deliberate — discrete diffusion forward masking
# already regularises; dropout on top is redundant.
dropout: 0.0
ema_decay: 0.999

# ── Diffusion (MDLM) ─────────────────────────────────────────────────
noise_schedule: linear
num_diffusion_steps: 100
loss_weight_clip: 1000.0
label_smoothing: 0.0
# Use SUBS importance weighting w(t) in loss. Off by default (flat average
# matching reference). Enable for MDLM ELBO experiments.
use_importance_weighting: false
# ReMDM stochastic remask base fraction
eta: 0.18
# Remasking strategy: rescale | cap | conf
remask_strategy: conf

# ── Inference ─────────────────────────────────────────────────────────
# Number of reverse denoising steps at inference.
# Reference uses 5 (aggressive). Higher = better quality, slower.
diffusion_steps_eval: 10
diffusion_steps_collect: 5
temperature: 0.5
top_k: 4
replan_every: 16
# Soft-penalise hazardous cardinal actions during stochastic sampling.
# Not active in the reference evaluation pipeline; off by default.
physics_aware_sampling: false

# ── Training budget (unified) ────────────────────────────────────────
total_timesteps: 20000000
id_eval_every_timesteps: 250000
ood_eval_every_timesteps: 250000
checkpoint_every_timesteps: 1250000

# ── Offline BC ────────────────────────────────────────────────────────
offline_lr: 0.0003
offline_batch_size: 6144
offline_grad_clip: 1.0
aux_loss_weight: 0.5

# ── DAgger ────────────────────────────────────────────────────────────
dagger_lr: 0.00003
dagger_batch_size: 6144
dagger_grad_clip: 1.0
weight_decay: 0.0001
buffer_capacity: 10000
episodes_per_iteration: 30
grad_steps_per_iteration: 100
efficiency_multiplier: 1.5
curriculum_queue_size: 100
# Pre-seed curriculum queues with 50/50 prior for uniform early sampling.
curriculum_preseed: true
eval_episodes_per_env: 50
checkpoint_eval_episodes: 50

# ── Performance ──────────────────────────────────────────────────────
# Mixed-precision (FP16) training via torch.cuda.amp.
# Speeds up forward/backward ~1.5-2x on GPU. No effect on CPU.
use_amp: true
# torch.compile the model for fused kernels (experimental).
# May cause slow first iteration due to compilation. No effect on CPU.
torch_compile: true
# Number of parallel workers for DAgger episode collection.
# 0 = sequential (reference behaviour). Recommended: 4-8 on multi-core.
num_collection_workers: 8

# ── Checkpointing & Logging ──────────────────────────────────────────
checkpoint_dir: checkpoints_ucl_learning_behaviour
save_policy: true
hub_run_id: null
hub_repo_id: null
use_wandb: true
wandb_project: remdm-minihack
wandb_entity: "mathis-weil-university-college-london-ucl-"
wandb_run_name: null
offline_log_every: 10
seed: null