Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy
An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot's ability to learn and adapt at runtime, leading to overly conservative behavior. This paper proposes a new closed-loop paradigm for synthesizing safe control policies that explicitly account for the robot's evolving uncertainty and its ability to quickly respond to future scenarios as they arise, by jointly considering the physical dynamics and the robot's learning algorithm. We leverage adversarial reinforcement learning for tractable safety analysis under high-dimensional learning dynamics and demonstrate our framework's ability to work with both Bayesian belief propagation and implicit learning through large pre-trained neural trajectory predictors.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous VehiclesReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Deception in Oligopoly Games via Adaptive Nash Seeking Systems
In the theory of multi-agent systems, deception refers to the strategic manipulation of information to influence the behavior of other agents, ultimately altering the long-term dynamics of the entire system. Recently, th…
Honesty Is the Best Policy: Defining and Mitigating AI Deception
Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with la…
PhilosophyHidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games
Large Language Model (LLM) agents are increasingly used in many applications, raising concerns about their safety. While previous work has shown that LLMs can deceive in controlled tasks, less is known about their abilit…
RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue
The original Turing Test asks a human judge to distinguish a machine from a person through dialogue. Three quarters of a century later, conversational systems pass this test in casual settings; the interesting epistemolo…
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabilities is fundamental to safety. Controlled social deduction games pr…