arXiv subjects

Anca Dragan

Publications and source records attributed to Anca Dragan.

At least 55 records · Page 3Linked to original sources

arXiv2023

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this popularity, there has been relatively little public work systematizing its flaws. In this paper, we (1) survey open problems and fundamental limitations of RLHF and related methods; (2) overview techniques to understand, improve, and complement RLHF in practice; and (3) propose auditing and disclosure standards to improve societal oversight of RLHF systems. Our work emphasizes the limitations of RLHF and highlights the importance of a multi-faceted approach to the development of safer AI systems.

cs.AI↗

arXiv2023

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Our goal is for robots to follow natural language instructions like "put the towel next to the microwave." But getting large amounts of labeled data, i.e. data that contains demonstrations of tasks labeled with the language instruction, is prohibitive. In contrast, obtaining policies that respond to image goals is much easier, because any autonomous trial or demonstration can be labeled in hindsight with its final state as the goal. In this work, we contribute a method that taps into joint image- and goal- conditioned policies with language using only a small amount of language data. Prior work has made progress on this using vision-language models or by jointly training language-goal-conditioned policies, but so far neither method has scaled effectively to real-world robot tasks without significant human annotation. Our method achieves robust performance in the real world by learning an embedding from the labeled data that aligns language not to the goal image, but rather to the desired change between the start and goal images that the instruction corresponds to. We then train a policy on this embedding: the policy benefits from all the unlabeled data, but the aligned embedding provides an interface for language to steer the policy. We show instruction following across a variety of manipulation tasks in different scenes, with generalization to language instructions outside of the labeled data. Videos and code for our approach can be found on our website: https://rail-berkeley.github.io/grif/ .

cs.RO↗

arXiv2023

Automatically Auditing Large Language Models via Discrete Optimization

Auditing large language models for unexpected behaviors is critical to preempt catastrophic deployments, yet remains challenging. In this work, we cast auditing as an optimization problem, where we automatically search for input-output pairs that match a desired target behavior. For example, we might aim to find a non-toxic input that starts with "Barack Obama" that a model maps to a toxic output. This optimization problem is difficult to solve as the set of feasible points is sparse, the space is discrete, and the language models we audit are non-linear and high-dimensional. To combat these challenges, we introduce a discrete optimization algorithm, ARCA, that jointly and efficiently optimizes over inputs and outputs. Our approach automatically uncovers derogatory completions about celebrities (e.g. "Barack Obama is a legalized unborn" -> "child murderer"), produces French inputs that complete to English outputs, and finds inputs that generate a specific name. Our work offers a promising new tool to uncover models' failure-modes before deployment.

cs.LG↗

arXiv2023

Towards Modeling and Influencing the Dynamics of Human Learning

Humans have internal models of robots (like their physical capabilities), the world (like what will happen next), and their tasks (like a preferred goal). However, human internal models are not always perfect: for example, it is easy to underestimate a robot's inertia. Nevertheless, these models change and improve over time as humans gather more experience. Interestingly, robot actions influence what this experience is, and therefore influence how people's internal models change. In this work we take a step towards enabling robots to understand the influence they have, leverage it to better assist people, and help human models more quickly align with reality. Our key idea is to model the human's learning as a nonlinear dynamical system which evolves the human's internal model given new observations. We formulate a novel optimization problem to infer the human's learning dynamics from demonstrations that naturally exhibit human learning. We then formalize how robots can influence human learning by embedding the human's learning dynamics model into the robot planning problem. Although our formulations provide concrete problem statements, they are intractable to solve in full generality. We contribute an approximation that sacrifices the complexity of the human internal models we can represent, but enables robots to learn the nonlinear dynamics of these internal models. We evaluate our inference and planning methods in a suite of simulated environments and an in-person user study, where a 7DOF robotic arm teaches participants to be better teleoperators. While influencing human learning remains an open problem, our results demonstrate that this influence is possible and can be helpful in real human-robot interaction.

cs.RO↗

arXiv2022

Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making, where many well-studied tasks like behavior cloning, offline RL, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns. We introduce the FlexiBiT framework, which provides a unified way to specify models which can be trained on many different sequential decision making tasks. We show that a single FlexiBiT model is simultaneously capable of carrying out many tasks with performance similar to or better than specialized models. Additionally, we show that performance can be further improved by fine-tuning our general model on specific tasks of interest.

cs.LG↗

arXiv2022

Time-Efficient Reward Learning via Visually Assisted Cluster Ranking

One of the most successful paradigms for reward learning uses human feedback in the form of comparisons. Although these methods hold promise, human comparison labeling is expensive and time consuming, constituting a major bottleneck to their broader applicability. Our insight is that we can greatly improve how effectively human time is used in these approaches by batching comparisons together, rather than having the human label each comparison individually. To do so, we leverage data dimensionality-reduction and visualization techniques to provide the human with a interactive GUI displaying the state space, in which the user can label subportions of the state space. Across some simple Mujoco tasks, we show that this high-level approach holds promise and is able to greatly increase the performance of the resulting agents, provided the same amount of human labeling time.

cs.LG↗

arXiv2022

UniMASK: Unified Inference in Sequential Decision Problems

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making, where many well-studied tasks like behavior cloning, offline reinforcement learning, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns. We introduce the UniMASK framework, which provides a unified way to specify models which can be trained on many different sequential decision-making tasks. We show that a single UniMASK model is often capable of carrying out many tasks with performance similar to or better than single-task models. Additionally, after fine-tuning, our UniMASK models consistently outperform comparable single-task models. Our code is publicly available at https://github.com/micahcarroll/uniMASK.

cs.LG↗

arXiv2022

Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration

AI agents designed to collaborate with people benefit from models that enable them to anticipate human behavior. However, realistic models tend to require vast amounts of human data, which is often hard to collect. A good prior or initialization could make for more data-efficient training, but what makes for a good prior on human behavior? Our work leverages a very simple assumption: people generally act closer to optimal than to random chance. We show that using optimal behavior as a prior for human models makes these models vastly more data-efficient and able to generalize to new environments. Our intuition is that such a prior enables the training to focus one's precious real-world data on capturing the subtle nuances of human suboptimality, instead of on the basics of how to do the task in the first place. We also show that using these improved human models often leads to better human-AI collaboration performance compared to using models based on real human data alone.

cs.LG↗

arXiv2022

Estimating and Penalizing Induced Preference Shifts in Recommender Systems

The content that a recommender system (RS) shows to users influences them. Therefore, when choosing a recommender to deploy, one is implicitly also choosing to induce specific internal states in users. Even more, systems trained via long-horizon optimization will have direct incentives to manipulate users: in this work, we focus on the incentive to shift user preferences so they are easier to satisfy. We argue that - before deployment - system designers should: estimate the shifts a recommender would induce; evaluate whether such shifts would be undesirable; and perhaps even actively optimize to avoid problematic shifts. These steps involve two challenging ingredients: estimation requires anticipating how hypothetical algorithms would influence user preferences if deployed - we do this by using historical user interaction data to train a predictive user model which implicitly contains their preference dynamics; evaluation and optimization additionally require metrics to assess whether such influences are manipulative or otherwise unwanted - we use the notion of "safe shifts", that define a trust region within which behavior is safe: for instance, the natural way in which users would shift without interference from the system could be deemed "safe". In simulated experiments, we show that our learned preference dynamics model is effective in estimating user preferences and how they would respond to new recommenders. Additionally, we show that recommenders that optimize for staying in the trust region can avoid manipulative behaviors while still generating engagement.

cs.LG↗

arXiv2022

The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume human behavior to be noisily-optimal for some reward function. The former are very useful, but only when it is possible to gather a lot of human data in the target environment and distribution. The advantage of the latter type, which includes Boltzmann rationality, is the ability to make accurate predictions in new environments without extensive data when humans are actually close to optimal. However, these models fail when humans exhibit systematic suboptimality, i.e. when their deviations from optimal behavior are not independent, but instead consistent over time. Our key insight is that systematic suboptimality can be modeled by predicting policies, which couple action choices over time, instead of trajectories. We introduce the Boltzmann policy distribution (BPD), which serves as a prior over human policies and adapts via Bayesian inference to capture systematic deviations by observing human actions during a single episode. The BPD is difficult to compute and represent because policies lie in a high-dimensional continuous space, but we leverage tools from generative and sequence models to enable efficient sampling and inference. We show that the BPD enables prediction of human behavior and human-AI collaboration equally as well as imitation learning-based human models while using far less data.

cs.AI↗

arXiv2022

Inferring Rewards from Language in Context

In classic instruction following, language like "I'd like the JetBlue flight" maps to actions (e.g., selecting that flight). However, language also conveys information about a user's underlying reward function (e.g., a general preference for JetBlue), which can allow a model to carry out desirable actions in new contexts. We present a model that infers rewards from language pragmatically: reasoning about how speakers choose utterances not only to elicit desired actions, but also to reveal information about their preferences. On a new interactive flight-booking task with natural language, our model more accurately infers rewards and predicts optimal actions in unseen environments, in comparison to past work that first maps language to actions (instruction following) and then maps actions to rewards (inverse reinforcement learning).

cs.CL↗

arXiv2021

Human irrationality: both bad and good for reward inference

Assuming humans are (approximately) rational enables robots to infer reward functions by observing human behavior. But people exhibit a wide array of irrationalities, and our goal with this work is to better understand the effect they can have on reward inference. The challenge with studying this effect is that there are many types of irrationality, with varying degrees of mathematical formalization. We thus operationalize irrationality in the language of MDPs, by altering the Bellman optimality equation, and use this framework to study how these alterations would affect inference. We find that wrongly modeling a systematically irrational human as noisy-rational performs a lot worse than correctly capturing these biases -- so much so that it can be better to skip inference altogether and stick to the prior! More importantly, we show that an irrational human, when correctly modelled, can communicate more information about the reward than a perfectly rational human can. That is, if a robot has the correct model of a human's irrationality, it can make an even stronger inference than it ever could if the human were rational. Irrationality fundamentally helps rather than hinder reward inference, but it needs to be correctly accounted for.

cs.LG↗

arXiv2021

B-Pref: Benchmarking Preference-Based Reinforcement Learning

Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a teacher's preferences without pre-defined rewards, thus overcoming concerns associated with reward engineering. However, it is difficult to quantify the progress in preference-based RL due to the lack of a commonly adopted benchmark. In this paper, we introduce B-Pref: a benchmark specially designed for preference-based RL. A key challenge with such a benchmark is providing the ability to evaluate candidate algorithms quickly, which makes relying on real human input for evaluation prohibitive. At the same time, simulating human input as giving perfect preferences for the ground truth reward function is unrealistic. B-Pref alleviates this by simulating teachers with a wide array of irrationalities, and proposes metrics not solely for performance but also for robustness to these potential irrationalities. We showcase the utility of B-Pref by using it to analyze algorithmic design choices, such as selecting informative queries, for state-of-the-art preference-based RL algorithms. We hope that B-Pref can serve as a common starting point to study preference-based RL more systematically. Source code is available at https://github.com/rll-research/B-Pref.

cs.LG↗

arXiv2021

The MineRL BASALT Competition on Learning from Human Feedback

The last decade has seen a significant increase of interest in deep learning research, with many public successes that have demonstrated its potential. As such, these systems are now being incorporated into commercial products. With this comes an additional challenge: how can we build AI systems that solve tasks where there is not a crisp, well-defined specification? While multiple solutions have been proposed, in this competition we focus on one in particular: learning from human feedback. Rather than training AI systems using a predefined reward function or using a labeled dataset with a predefined set of categories, we instead train the AI system using a learning signal derived from some form of human feedback, which can evolve over time as the understanding of the task changes, or as the capabilities of the AI system improve. The MineRL BASALT competition aims to spur forward research on this important class of techniques. We design a suite of four tasks in Minecraft for which we expect it will be hard to write down hardcoded reward functions. These tasks are defined by a paragraph of natural language: for example, "create a waterfall and take a scenic picture of it", with additional clarifying details. Participants must train a separate agent for each task, using any method they want. Agents are then evaluated by humans who have read the task description. To help participants get started, we provide a dataset of human demonstrations on each of the four tasks, as well as an imitation learning baseline that leverages these demonstrations. Our hope is that this competition will improve our ability to build AI systems that do what their designers intend them to do, even when the intent cannot be easily formalized. Besides allowing AI to solve more tasks, this can also enable more effective regulation of AI systems, as well as making progress on the value alignment problem.

cs.LG↗

arXiv2021

Learning What To Do by Simulating the Past

Since reward functions are hard to specify, recent work has focused on learning policies from human feedback. However, such approaches are impeded by the expense of acquiring such feedback. Recent work proposed that agents have access to a source of information that is effectively free: in any environment that humans have acted in, the state will already be optimized for human preferences, and thus an agent can extract information about what humans want from the state. Such learning is possible in principle, but requires simulating all possible past trajectories that could have led to the observed state. This is feasible in gridworlds, but how do we scale it to complex tasks? In this work, we show that by combining a learned feature encoder with learned inverse models, we can enable agents to simulate human actions backwards in time to infer what they must have done. The resulting algorithm is able to reproduce a specific skill in MuJoCo environments given a single state sampled from the optimal policy for that skill.

cs.LG↗

arXiv2021

Choice Set Misspecification in Reward Inference

Specifying reward functions for robots that operate in environments without a natural reward signal can be challenging, and incorrectly specified rewards can incentivise degenerate or dangerous behavior. A promising alternative to manually specifying reward functions is to enable robots to infer them from human feedback, like demonstrations or corrections. To interpret this feedback, robots treat as approximately optimal a choice the person makes from a choice set, like the set of possible trajectories they could have demonstrated or possible corrections they could have made. In this work, we introduce the idea that the choice set itself might be difficult to specify, and analyze choice set misspecification: what happens as the robot makes incorrect assumptions about the set of choices from which the human selects their feedback. We propose a classification of different kinds of choice set misspecification, and show that these different classes lead to meaningful differences in the inferred reward and resulting performance. While we would normally expect misspecification to hurt, we find that certain kinds of misspecification are neither helpful nor harmful (in expectation). However, in other situations, misspecification can be extremely harmful, leading the robot to believe the opposite of what it should believe. We hope our results will allow for better prediction and response to the effects of misspecification in real-world reward inference.

cs.AI↗

arXiv2021

AvE: Assistance via Empowerment

One difficulty in using artificial agents for human-assistive applications lies in the challenge of accurately assisting with a person's goal(s). Existing methods tend to rely on inferring the human's goal, which is challenging when there are many potential goals or when the set of candidate goals is difficult to identify. We propose a new paradigm for assistance by instead increasing the human's ability to control their environment, and formalize this approach by augmenting reinforcement learning with human empowerment. This task-agnostic objective preserves the person's autonomy and ability to achieve any eventual state. We test our approach against assistance based on goal inference, highlighting scenarios where our method overcomes failure modes stemming from goal ambiguity or misspecification. As existing methods for estimating empowerment in continuous domains are computationally hard, precluding its use in real time learned assistance, we also propose an efficient empowerment-inspired proxy metric. Using this, we are able to successfully demonstrate our method in a shared autonomy user study for a challenging simulated teleoperation task with human-in-the-loop training.

cs.AI↗

arXiv2020

Inverse Reward Design

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training scenarios, and make sure that the reward will lead to the right behavior in those scenarios. Inevitably, agents encounter new scenarios (e.g., new types of terrain) where optimizing that same reward may lead to undesired behavior. Our insight is that reward functions are merely observations about what the designer actually wants, and that they should be interpreted in the context in which they were designed. We introduce inverse reward design (IRD) as the problem of inferring the true objective based on the designed reward and the training MDP. We introduce approximate methods for solving IRD problems, and use their solution to plan risk-averse behavior in test MDPs. Empirical results suggest that this approach can help alleviate negative side effects of misspecified reward functions and mitigate reward hacking.

cs.AI↗