Global decarbonisation targets and tightening market pressures demand maritime logistics solutions that are simultaneously efficient, sustainable, and equitable. We introduce EcoFair-CH-MARL, a constrained hierarchical multi-agent reinforcement learning framework that unifies three innovations: (i) a primal-dual budget layer that provably bounds cumulative emissions under stochastic weather and demand; (ii) a fairness-aware reward transformer with dynamically scheduled penalties that enforces max-min cost equity across heterogeneous fleets; and (iii) a two-tier policy architecture that decouples strategic routing from real-time vessel control, enabling linear scaling in agent count. New theoretical results establish O(\sqrt{T}) regret for both constraint violations and fairness loss. Experiments on a high-fidelity maritime digital twin (16 ports, 50 vessels) driven by automatic identification system traces, plus an energy-grid case study, show up to 15% lower emissions, 12% higher through-put, and a 45% fair-cost improvement over state-of-the-art hierarchical and constrained MARL baselines. In addition, EcoFair-CH-MARL achieves stronger equity (lower Gini and higher min-max welfare) than fairness-specific MARL baselines (e.g., SOTO, FEN), and its modular design is compatible with both policy- and value-based learners. EcoFair-CH-MARL therefore advances the feasibility of large-scale, regulation-compliant, and socially responsible multi-agent coordination in safety-critical domains.
Figures & tables
Figure 1: CH‑MARL with high‑level routing/budgeting and low‑level control under primal–dual (constraint) and fairness layers (CTDE training, decentralised execution).
Method (Algo)
Gini ( ↓ )
Min–Max ( ↑ )
PPO
0.124±0.143
0.624±0.433
SOTO
0.225±0.126
0.320±0.381
FEN
0.292±0.000
0.476±0.000
MAPPO
0.139±0.000
0.639±0.000
QMIX
0.000
1.000
Table 1: Fairness metrics on 16 ports / 50 vessels (mean ± std across runs). Lower Gini and higher min–max are better. The PPO row is EcoFair‑CH‑MARL (PPO).
Figure 2: Per‑episode Gini (16 ports / 50 vessels; mean across runs). Lower is better.
Method (Algo)
Return
Emissions
PPO
−989.004±128.238
–
SOTO
−1054.813±92.835
–
FEN
−533.465±0.000
–
MAPPO
−1190.169±0.000
–
QMIX
−1623.473±0.000
–
Table 2: Performance on 16 ports / 50 vessels (mean ± std across runs). Negative returns follow the environment’s cost convention; lower emissions are better.
Method (Algo)
Return (final)
Emissions (final)
PPO
−1091.626±166.533
–
SOTO
−1115.668±79.281
–
FEN
−538.028±0.000
–
MAPPO
−1190.169±0.000
–
QMIX
−1623.473±0.000
–
Table 3: Final‑iteration outcomes (last episode; mean ± std across runs) on 16 ports / 50 vessels.