Victor Mylle
8cc84d6a21
Added a temporal observation history buffer and 1D-CNN encoder so the
policy can implicitly infer environment parameters (mass, friction,
gear ratios, etc.) from recent (obs, action) dynamics.
Architecture:
history window [(obs₀,a₀), ..., (obs_{H-1},a_{H-1})]
→ 1D-CNN HistoryEncoder → embedding (32-dim)
→ concat [current_obs, embedding] → MLP → action
Components:
- BaseRunner: history ring buffer, _push_history/_reset_history,
augmented obs space (6 + H×7 = 76 with H=10)
- HistoryEncoder (src/models/mlp.py): 2-layer temporal Conv1d + GAP
- SharedMLP: optional history_length/raw_obs_dim/embedding_dim params;
splits augmented obs, encodes history, feeds [obs, emb] to MLP
- TrainerConfig: history_length, embedding_dim fields
- All runner configs: history_length=10 by default
- Tests: encoder shape, model with/without history, config defaults
9 lines
209 B
YAML
9 lines
209 B
YAML
# Single-env MuJoCo runner — mimics real hardware timing.
|
||
# dt × substeps = 0.002 × 10 = 0.02 s → 50 Hz control, same as serial runner.
|
||
|
||
num_envs: 1
|
||
device: cpu
|
||
dt: 0.002
|
||
substeps: 10
|
||
history_length: 10
|