相关论文: Robust Autonomy Emerges from Self-Play

This paper presents a robust reinforcement learning algorithm called robust deterministic policy gradient (RDPG), which reformulates the H-infinity control problem as a two-player zero-sum dynamic game between a user and an adversary. The…

This work in progress considers reachability-based safety analysis in the domain of autonomous driving in multi-agent systems. We formulate the safety problem for a car following scenario as a differential game and study how different…

Fleets of autonomous vehicles can mitigate traffic congestion through simple actions, thus improving many socioeconomic factors such as commute time and gas costs. However, these approaches are limited in practice as they assume precise…

Reinforcement-based learning dynamics may exhibit several limitations when applied in a distributed setup. In (repeatedly-played) multi-player/action strategic-form games, and when each player applies an independent copy of the learning…

Off-road navigation is a challenging problem both at the planning level to get a smooth trajectory and at the control level to avoid flipping over, hitting obstacles, or getting stuck at a rough patch. There have been several recent works…

Data-driven simulators promise high data-efficiency for driving policy learning. When used for modelling interactions, this data-efficiency becomes a bottleneck: Small underlying datasets often lack interesting and challenging edge cases…

Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either address safety requirements under the assumption of no…

The ability to guarantee safety and progress for all vehicles is vital to the success of the autonomous vehicle industry. We present a framework for designing autonomous vehicle behavior in a way that is safe and guarantees progress for all…

Traffic congestion and collisions represent significant economic, environmental, and social challenges worldwide. Traditional traffic management approaches have shown limited success in addressing these complex, dynamic problems. To address…

Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain,…

We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play for goal discovery, where two agents, Alice and Bob, play a…

Two traditional paradigms are often used to describe the behavior of agents in multi-agent complex systems. In the first one, agents are considered to be fully rational and systems are seen as multi-player games. In the second one, agents…

Achieving highly dynamic behaviors on humanoid robots, such as running, requires controllers that are both robust and precise, and hence difficult to design. Classical control methods offer valuable insight into how such systems can…

Large language models (LLMs) have advanced rapidly in recent years, driven by scale, abundant high-quality training data, and reinforcement learning. Yet this progress faces a fundamental bottleneck: the need for ever more data from which…

Starting from a heuristic learning scheme for N-person games, we derive a new class of continuous-time learning dynamics consisting of a replicator-like drift adjusted by a penalty term that renders the boundary of the game's strategy space…

Many decision-making scenarios in modern life benefit from the decision support of artificial intelligence algorithms, which focus on a data-driven philosophy and automated programs or systems. However, crucial decision issues related to…

Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured…

This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error…

Most self-driving systems rely on hand-coded perception outputs and engineered driving rules. Learning directly from human driving data with an end-to-end method can allow for a training architecture that is simpler and scales well with…

Autonomous Braking and Throttle control is key in developing safe driving systems for the future. There exists a need for autonomous vehicles to negotiate a multi-agent environment while ensuring safety and comfort. A Deep Reinforcement…