Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making
This work addresses tactical decision making for autonomous driving systems, but it appears incremental as it builds on existing deep reinforcement learning methods with specific enhancements.
The paper tackled the problem of tactical driving decision making for autonomous vehicles by proposing three practical components to speed up deep reinforcement learning, resulting in superior performance in safety, efficiency, and comfort compared to baselines in a realistic simulator.
Tactical driving decision making is crucial for autonomous driving systems and has attracted considerable interest in recent years. In this paper, we propose several practical components that can speed up deep reinforcement learning algorithms towards tactical decision making tasks: 1) non-uniform action skipping as a more stable alternative to action-repetition frame skipping, 2) a counter-based penalty for lanes on which ego vehicle has less right-of-road, and 3) heuristic inference-time action masking for apparently undesirable actions. We evaluate the proposed components in a realistic driving simulator and compare them with several baselines. Results show that the proposed scheme provides superior performance in terms of safety, efficiency, and comfort.