Upload folder using huggingface_hub

gridops/models.py

@@ -37,7 +37,7 @@ class GridOpsAction(Action):
         default=0.0,
         ge=0.0,
         le=1.0,
-        description="Demand response: 0 (none) to 1 (shed 20%). 50% rebounds next hour.",
+        description="Demand response: 0 (none) to 1 (shed 20%). 100% rebounds next hour. Rs 40/kWh penalty.",
     )
 
 

gridops/server/static/index.html

@@ -409,7 +409,7 @@
       <p style="margin-left:8px; line-height: 2.0;">
         &#128267; <strong>Battery</strong> &mdash; charge it (store cheap energy) or discharge it (cover peaks)<br>
         &#9981; <strong>Diesel</strong> &mdash; turn it on for emergency power (expensive!)<br>
-        &#127968; <strong>Demand shed</strong> &mdash; ask residents to use less (but 50% rebounds next hour)
+        &#127968; <strong>Demand shed</strong> &mdash; ask residents to use less (but 100% rebounds next hour)
       </p>
     </div>
 
@@ -438,7 +438,7 @@
       <div class="cp-item">
         <span class="cp-icon">&#127968;</span>
         <div class="cp-name">Demand Shed</div>
-        <div class="cp-desc">Ask residents to cut usage. Up to 20%. 50% rebounds next hour.</div>
+        <div class="cp-desc">Ask residents to cut usage. Up to 20%. 100% rebounds next hour! Rs 40/kWh.</div>
       </div>
     </div>
 

gridops/simulation/physics.py

@@ -7,7 +7,7 @@ KEY DESIGN (per Gemini review):
   - VoLL penalty (Rs 150/kWh) replaces hard reliability gate
   - Battery degradation cost (Rs 2.5/kWh throughput)
   - Diesel startup cost (Rs 100 if was off last step)
-  - Demand shedding rebound (50% of shed kWh added to next hour)
+  - Demand shedding rebound (100% of shed kWh deferred to next hour)
 """
 
 from __future__ import annotations
@@ -123,7 +123,7 @@ def step(
     actual_demand = demand_kw + state.shed_rebound_kwh / DT  # rebound is kWh, convert to kW
     effective_demand = actual_demand * (1.0 - shed_frac)
     shed_kwh = actual_demand * shed_frac * DT
-    state.shed_rebound_kwh = shed_kwh * SHED_REBOUND_FRAC  # 50% rebounds next hour
+    state.shed_rebound_kwh = shed_kwh * SHED_REBOUND_FRAC  # 100% rebounds next hour
 
     # ── Diesel fuel constraint ───────────────────────────────────────
     available_diesel_kwh = state.diesel_fuel_kwh
@@ -227,9 +227,13 @@ def step(
     state.last_cost = step_cost
     state.last_grid_kw = grid_kw
 
-    # ── Per-step reward (negative cost, normalized) ──────────────────
-    # Simple: reward = -cost / normalization. Agent minimizes total cost.
-    reward = -step_cost / 500.0  # normalize to roughly [-2, 0] range
+    # ── Per-step reward (aligned with episode grader weights) ────────
+    # Grader = 50% cost_efficiency + 25% reliability + 25% green_score
+    # Step reward mirrors these proportions for consistent learning signal.
+    cost_signal = -step_cost / 500.0
+    reliability_signal = -2.0 * (blackout_kwh / max(effective_demand * DT, 1.0))
+    green_signal = -0.5 * (diesel_kw / DIESEL_MAX_KW) if diesel_kw > 0 else 0.0
+    reward = 0.50 * cost_signal + 0.25 * reliability_signal + 0.25 * green_signal
     state.last_reward = reward
 
     # ── Advance clock ────────────────────────────────────────────────

inference.py

@@ -38,7 +38,7 @@ You are an expert microgrid operator managing a 100-home community in India duri
 You control three actions each hour:
 - battery_dispatch: -1 (charge 100 kW from grid) to +1 (discharge 100 kW to community)
 - diesel_dispatch: 0 (off) to 1 (100 kW). Costs Rs 25/kWh + Rs 100 startup if was off.
-- demand_shedding: 0 (none) to 1 (shed 20% of demand). WARNING: 50% rebounds next hour.
+- demand_shedding: 0 (none) to 1 (shed 20% of demand). WARNING: 100% rebounds next hour! Rs 40/kWh penalty.
 
 The GRID automatically absorbs the residual (capped at ±200 kW).
 If demand exceeds grid + solar + battery + diesel → BLACKOUT (Rs 150/kWh penalty!).

openenv.yaml

@@ -32,7 +32,7 @@ tasks:
     description: "Full 3-day heatwave, -30% solar, Rs 8-20 prices, limited diesel fuel."
 
 metadata:
-  action_space: "3D continuous: grid_trade [-1,1], diesel_dispatch [0,1], demand_shedding [0,1]"
+  action_space: "3D continuous: battery_dispatch [-1,1], diesel_dispatch [0,1], demand_shedding [0,1]"
   observation_space: "12 fields: hour, demand, solar, battery_soc, price, fuel, 3×4h forecasts, cumulative metrics"
   episode_length: 72
   step_duration: "1 hour"