Efficient Exploration at Scale

We develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our algorithm incrementally updates reward and language models as choice data is received. The reward model is fit to the choice data, while the language model is updated by a variation of reinforce, with reinforcement signals provided by the reward model. Several features enable the efficiency gains: a small affirmative nudge added to each reinforcement signal, an epistemic neural network that models reward uncertainty, and information-directed exploration. With Gemma large language models (LLMs), our algorithm matches the performance of offline RLHF trained on 200K labels using fewer than 20K labels, representing more than a 10x gain in data efficiency. Extrapolating from our results, we expect our algorithm trained on 1M labels to match offline RLHF trained on 1B labels. This represents a 1,000x gain. To our knowledge, these are the first results to demonstrate that such large improvements are possible.

Consequentialist Objectives and Catastrophe

Because human preferences are too complex to codify, AIs operate with misspecified objectives. Optimizing such objectives often produces undesirable outcomes; this phenomenon is known as reward hacking. Such outcomes are not necessarily catastrophic. Indeed, most examples of reward hacking in previous literature are benign. And typically, objectives can be modified to resolve the issue. We study the prospect of catastrophic outcomes induced by AIs operating in complex environments. We argue that, when capabilities are sufficiently advanced, pursuing a fixed consequentialist objective tends to result in catastrophic outcomes. We formalize this by establishing conditions that provably lead to such outcomes. Under these conditions, simple or random behavior is safe. Catastrophic risk arises due to extraordinary competence rather than incompetence. With a fixed consequentialist objective, avoiding catastrophe requires constraining AI capabilities. In fact, constraining capabilities the right amount not only averts catastrophe but yields valuable outcomes. Our results apply to any objective produced by modern industrial AI development pipelines.

Prior Diffusiveness and Regret in the Linear-Gaussian Bandit

We prove that Thompson sampling exhibits $\tilde{O}(σd \sqrt{T} + d r \sqrt{\mathrm{Tr}(Σ_0)})$ Bayesian regret in the linear-Gaussian bandit with a $\mathcal{N}(μ_0, Σ_0)$ prior distribution on the coefficients, where $d$ is the dimension, $T$ is the time horizon, $r$ is the maximum $\ell_2$ norm of the actions, and $σ^2$ is the noise variance. In contrast to existing regret bounds, this shows that to within logarithmic factors, the prior-dependent ``burn-in'' term $d r \sqrt{\mathrm{Tr}(Σ_0)}$ decouples additively from the minimax (long run) regret $σd \sqrt{T}$. Previous regret bounds exhibit a multiplicative dependence on these terms. We establish these results via a new ``elliptical potential'' lemma, and also provide a lower bound indicating that the burn-in term is unavoidable.

Granular feedback merits sophisticated aggregation

Human feedback is increasingly used across diverse applications like training AI models, developing recommender systems, and measuring public opinion -- with granular feedback often being preferred over binary feedback for its greater informativeness. While it is easy to accurately estimate a population's distribution of feedback given feedback from a large number of individuals, cost constraints typically necessitate using smaller groups. A simple method to approximate the population distribution is regularized averaging: compute the empirical distribution and regularize it toward a prior. Can we do better? As we will discuss, the answer to this question depends on feedback granularity. Suppose one wants to predict a population's distribution of feedback using feedback from a limited number of individuals. We show that, as feedback granularity increases, one can substantially improve upon predictions of regularized averaging by combining individuals' feedback in ways more sophisticated than regularized averaging. Our empirical analysis using questions on social attitudes confirms this pattern. In particular, with binary feedback, sophistication barely reduces the number of individuals required to attain a fixed level of performance. By contrast, with five-point feedback, sophisticated methods match the performance of regularized averaging with about half as many individuals.

Choice between Partial Trajectories

As AI agents generate increasingly sophisticated behaviors, manually encoding human preferences to guide these agents becomes more challenging. To address this, it has been suggested that agents instead learn preferences from human choice data. This approach requires a model of choice behavior that the agent can use to interpret the data. For choices between partial trajectories of states and actions, previous models assume choice probabilities to be determined by the partial return or the cumulative advantage. We consider an alternative model based instead on the bootstrapped return, which adds to the partial return an estimate of the future return. Benefits of the bootstrapped return model stem from its treatment of human beliefs. Unlike partial return, choices based on bootstrapped return reflect human beliefs about the environment. Further, while recovering the reward function from choices based on cumulative advantage requires that those beliefs are correct, doing so from choices based on bootstrapped return does not. To motivate the bootstrapped return model, we formulate axioms and prove an Alignment Theorem. This result formalizes how, for a general class of human preferences, such models are able to disentangle goals from beliefs. This ensures recovery of an aligned reward function when learning from choices based on bootstrapped return. The bootstrapped return model also affords greater robustness to choice behavior. Even when choices are based on partial return, learning via a bootstrapped return model recovers an aligned reward function. The same holds with choices based on the cumulative advantage if the human and the agent both adhere to correct and consistent beliefs about the environment. On the other hand, if choices are based on bootstrapped return, learning via partial return or cumulative advantage models does not generally produce an aligned reward function.

Aligning AI Agents via Information-Directed Sampling

The staggering feats of AI systems have brought to attention the topic of AI Alignment: aligning a "superintelligent" AI agent's actions with humanity's interests. Many existing frameworks/algorithms in alignment study the problem on a myopic horizon or study learning from human feedback in isolation, relying on the contrived assumption that the agent has already perfectly identified the environment. As a starting point to address these limitations, we define a class of bandit alignment problems as an extension of classic multi-armed bandit problems. A bandit alignment problem involves an agent tasked with maximizing long-run expected reward by interacting with an environment and a human, both involving details/preferences initially unknown to the agent. The reward of actions in the environment depends on both observed outcomes and human preferences. Furthermore, costs are associated with querying the human to learn preferences. Therefore, an effective agent ought to intelligently trade-off exploration (of the environment and human) and exploitation. We study these trade-offs theoretically and empirically in a toy bandit alignment problem which resembles the beta-Bernoulli bandit. We demonstrate while naive exploration algorithms which reflect current practices and even touted algorithms such as Thompson sampling both fail to provide acceptable solutions to this problem, information-directed sampling achieves favorable regret.

The Need for a Big World Simulator: A Scientific Challenge for Continual Learning

The "small agent, big world" frame offers a conceptual view that motivates the need for continual learning. The idea is that a small agent operating in a much bigger world cannot store all information that the world has to offer. To perform well, the agent must be carefully designed to ingest, retain, and eject the right information. To enable the development of performant continual learning agents, a number of synthetic environments have been proposed. However, these benchmarks suffer from limitations, including unnatural distribution shifts and a lack of fidelity to the "small agent, big world" framing. This paper aims to formalize two desiderata for the design of future simulated environments. These two criteria aim to reflect the objectives and complexity of continual learning in practical settings while enabling rapid prototyping of algorithms on a smaller scale.

Information-Theoretic Foundations for Machine Learning

The staggering progress of machine learning in the past decade has been a sight to behold. In retrospect, it is both remarkable and unsettling that these milestones were achievable with little to no rigorous theory to guide experimentation. Despite this fact, practitioners have been able to guide their future experimentation via observations from previous large-scale empirical investigations. However, alluding to Plato's Allegory of the cave, it is likely that the observations which form the field's notion of reality are but shadows representing fragments of that reality. In this work, we propose a theoretical framework which attempts to answer what exists outside of the cave. To the theorist, we provide a framework which is mathematically rigorous and leaves open many interesting ideas for future exploration. To the practitioner, we provide a framework whose results are very intuitive, general, and which will help form principles to guide future investigations. Concretely, we provide a theoretical framework rooted in Bayesian statistics and Shannon's information theory which is general enough to unify the analysis of many phenomena in machine learning. Our framework characterizes the performance of an optimal Bayesian learner, which considers the fundamental limits of information. Throughout this work, we derive very general theoretical results and apply them to derive insights specific to settings ranging from data which is independently and identically distributed under an unknown distribution, to data which is sequential, to data which exhibits hierarchical structure amenable to meta-learning. We conclude with a section dedicated to characterizing the performance of misspecified algorithms. These results are exciting and particularly relevant as we strive to overcome increasingly difficult machine learning challenges in this endlessly complex world.

Satisficing Exploration for Deep Reinforcement Learning

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world, however, attaining optimal performance may in fact be an entirely intractable endeavor and an agent may seldom find itself in a position to complete the requisite exploration for identifying an optimal policy. Recent work has leveraged tools from information theory to design agents that deliberately forgo optimal solutions in favor of sufficiently-satisfying or satisficing solutions, obtained through lossy compression. Notably, such agents may employ fundamentally different exploratory decisions to learn satisficing behaviors more efficiently than optimal ones that are more data intensive. While supported by a rigorous corroborating theory, the underlying algorithm relies on model-based planning, drastically limiting the compatibility of these ideas with function approximation and high-dimensional observations. In this work, we remedy this issue by extending an agent that directly represents uncertainty over the optimal value function allowing it to both bypass the need for model-based planning and to learn satisficing policies. We provide simple yet illustrative experiments that demonstrate how our algorithm enables deep reinforcement-learning agents to achieve satisficing behaviors. In keeping with previous work on this setting for multi-armed bandits, we additionally find that our algorithm is capable of synthesizing optimal behaviors, when feasible, more efficiently than its non-information-theoretic counterpart.

Exploration Unbound

A sequential decision-making agent balances between exploring to gain new knowledge about an environment and exploiting current knowledge to maximize immediate reward. For environments studied in the traditional literature, optimal decisions gravitate over time toward exploitation as the agent accumulates sufficient knowledge and the benefits of further exploration vanish. What if, however, the environment offers an unlimited amount of useful knowledge and there is large benefit to further exploration no matter how much the agent has learned? We offer a simple, quintessential example of such a complex environment. In this environment, rewards are unbounded and an agent can always increase the rate at which rewards accumulate by exploring to learn more. Consequently, an optimal agent forever maintains a propensity to explore.