A Controlled Study of Double DQN and Dueling DQN Under Cross-Environment Transfer

Transfer learning in deep reinforcement learning is often motivated by improved stability and reduced training cost, but it can also fail under substantial domain shift. This paper presents a controlled empirical study examining how architectural differences between Double Deep Q-Networks (DDQN) and Dueling DQN influence transfer behavior across environments. Using CartPole as a source task and LunarLander as a structurally distinct target task, we evaluate a fixed layer-wise representation transfer protocol under identical hyperparameters and training conditions, with baseline agents trained from scratch used to contextualize transfer effects. Empirical results show that DDQN consistently avoids negative transfer under the examined setup and maintains learning dynamics comparable to baseline performance in the target environment. In contrast, Dueling DQN consistently exhibits negative transfer under identical conditions, characterized by degraded rewards and unstable optimization behavior. Statistical analysis across multiple random seeds confirms a significant performance gap under transfer. These findings suggest that architectural inductive bias is strongly associated with robustness to cross-environment transfer in value-based deep reinforcement learning under the examined transfer protocol.

Embodiment-Induced Coordination Regimes in Tabular Multi-Agent Q-Learning

Centralized value learning is often assumed to improve coordination and stability in multi-agent reinforcement learning, yet this assumption is rarely tested under controlled conditions. We directly evaluate it in a fully tabular predator-prey gridworld by comparing independent and centralized Q-learning under explicit embodiment constraints on agent speed and stamina. Across multiple kinematic regimes and asymmetric agent roles, centralized learning fails to provide a consistent advantage and is frequently outperformed by fully independent learning, even under full observability and exact value estimation. Moreover, asymmetric centralized-independent configurations induce persistent coordination breakdowns rather than transient learning instability. By eliminating confounding effects from function approximation and representation learning, our tabular analysis isolates coordination structure as the primary driver of these effects. The results show that increased coordination can become a liability under embodiment constraints, and that the effectiveness of centralized learning is fundamentally regime and role dependent rather than universal.