Ted Fujimoto

Ted Fujimoto, Jacob Benz

The advancement of AI capabilities compels researchers and the public to be more aware of its potential worldwide impact. A pressing near-term concern is the regulation of military AI applications. Armament manufacturers and defense contractors are increasingly investing in AI capabilities and forging partnerships with AI companies, creating a burgeoning coalition that demands military leaders, arms control diplomacy experts, and AI researchers collaborate to ensure a safer future. While AI researchers often focus on the long-term implications of superintelligent AI, this approach may not adequately address the immediate challenges posed by AI in military applications. Success requires acknowledging and mitigating the emerging risks of frontier AI models that plan to be integrated into defense applications, like military AI systems. Arms control has reduced past catastrophic risks, so lessons learned from nuclear deterrence can guide AI safety and security research towards innovations in verification and diplomacy. AI researchers, however, must assist in leading the technical research that clearly defines and alleviates instability in military settings. Given these new responsibilities and the lack of sufficiently reliable solutions, we argue that AI researchers must take a leading role in advancing arms control research to minimize risk in military AI applications.

Ted Fujimoto, Joshua Suetterlein, Samrat Chatterjee et al.

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful convergence to the optimal policy during training, may obfuscate overfitting or dependence on the experimental setup. Although researchers in RL have proposed reliability metrics that account for uncertainty to better understand each algorithm's strengths and weaknesses, the recommendations of past work do not assume the presence of out-of-distribution observations. We propose a set of evaluation methods that measure the robustness of RL algorithms under distribution shifts. The tools presented here argue for the need to account for performance over time while the agent is acting in its environment. In particular, we recommend time series analysis as a method of observational RL evaluation. We also show that the unique properties of RL and simulated dynamic environments allow us to make stronger assumptions to justify the measurement of causal impact in our evaluations. We then apply these tools to single-agent and multi-agent environments to show the impact of introducing distribution shifts during test time. We present this methodology as a first step toward rigorous RL evaluation in the presence of distribution shifts.

Ted Fujimoto, Timothy Doster, Adam Attarian et al.

We investigate how effective an attacker can be when it only learns from its victim's actions, without access to the victim's reward. In this work, we are motivated by the scenario where the attacker wants to behave strategically when the victim's motivations are unknown. We argue that one heuristic approach an attacker can use is to maximize the entropy of the victim's policy. The policy is generally not obfuscated, which implies it may be extracted simply by passively observing the victim. We provide such a strategy in the form of a reward-free exploration algorithm that maximizes the attacker's entropy during the exploration phase, and then maximizes the victim's empirical entropy during the planning phase. In our experiments, the victim agents are subverted through policy entropy maximization, implying an attacker might not need access to the victim's reward to succeed. Hence, reward-free attacks, which are based only on observing behavior, show the feasibility of an attacker to act strategically without knowledge of the victim's motives even if the victim's reward information is protected.

Ted Fujimoto, Arthur Paul Pedersen

Single-agent reinforcement learning algorithms in a multi-agent environment are inadequate for fostering cooperation. If intelligent agents are to interact and work together to solve complex problems, methods that counter non-cooperative behavior are needed to facilitate the training of multiple agents. This is the goal of cooperative AI. Recent research in adversarial machine learning, however, shows that models (e.g., image classifiers) can be easily deceived into making inferior decisions. Meanwhile, an important line of research in cooperative AI has focused on introducing algorithmic improvements that accelerate learning of optimally cooperative behavior. We argue that prominent methods of cooperative AI are exposed to weaknesses analogous to those studied in prior machine learning research. More specifically, we show that three algorithms inspired by human-like social intelligence are, in principle, vulnerable to attacks that exploit weaknesses introduced by cooperative AI's algorithmic improvements and report experimental findings that illustrate how these vulnerabilities can be exploited in practice.

Ted Fujimoto

Complex systems show how surprising and beautiful phenomena can emerge from structures or agents following simple rules. With the recent success of deep reinforcement learning (RL), a natural path forward would be to use the capabilities of multiple deep RL agents to produce emergent behavior of greater benefit and sophistication. In general, this has proved to be an unreliable strategy without significant computation due to the difficulties inherent in multi-agent RL training. In this paper, we propose some criteria for creativity in multi-agent RL. We hope this proposal will give artists applying multi-agent RL a starting point, and provide a catalyst for further investigation guided by philosophical discussion.