Existing approaches to reward inference from behavior typically assume that humans provide demonstrations according to specific models of behavior. However, humans often indicate their goals through a wide range of behaviors, from actions that are suboptimal due to poor planning or execution to behaviors which are intended to communicate goals rather than achieve them. We propose that supervised learning offers a unified framework to infer reward functions from any class of behavior, and show that such an approach is asymptotically Bayes-optimal under mild assumptions. Experiments on simulated robotic manipulation tasks show that our method can efficiently infer rewards from a wide variety of arbitrarily suboptimal demonstrations.

Designing a reinforcement learning from human feedback (RLHF) algorithm to approximate a human's unobservable reward function requires assuming, implicitly or explicitly, a model of human preferences. A preference model that poorly describes how humans generate preferences risks learning a poor approximation of the human's reward function. In this paper, we conduct three human studies to asses whether one can influence the expression of real human preferences to more closely conform to a desired preference model. Importantly, our approach does not seek to alter the human's unobserved reward function. Rather, we change how humans use this reward function to generate preferences, such that they better match whatever preference model is assumed by a particular RLHF algorithm. We introduce three interventions: showing humans the quantities that underlie a preference model, which is normally unobservable information derived from the reward function; training people to follow a specific preference model; and modifying the preference elicitation question. All intervention types show significant effects, providing practical tools to improve preference data quality and the resultant alignment of the learned reward functions. Overall we establish a novel research direction in model alignment: designing interfaces and training interventions to increase human conformance with the modeling assumptions of the algorithm that will learn from their input.

Rewards remain an uninterpretable way to specify tasks for Reinforcement Learning, as humans are often unable to predict the optimal behavior of any given reward function, leading to poor reward design and reward hacking. Language presents an appealing way to communicate intent to agents and bypass reward design, but prior efforts to do so have been limited by costly and unscalable labeling efforts. In this work, we propose a method for a completely unsupervised alternative to grounding language instructions in a zero-shot manner to obtain policies. We present a solution that takes the form of imagine, project, and imitate: The agent imagines the observation sequence corresponding to the language description of a task, projects the imagined sequence to our target domain, and grounds it to a policy. Video-language models allow us to imagine task descriptions that leverage knowledge of tasks learned from internet-scale video-text mappings. The challenge remains to ground these generations to a policy. In this work, we show that we can achieve a zero-shot language-to-behavior policy by first grounding the imagined sequences in real observations of an unsupervised RL agent and using a closed-form solution to imitation learning that allows the RL agent to mimic the grounded observations. Our method, RLZero, is the first to our knowledge to show zero-shot language to behavior generation abilities without any supervision on a variety of tasks on simulated domains. We further show that RLZero can also generate policies zero-shot from cross-embodied videos such as those scraped from YouTube.

As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic outcomes. This paper experimentally evaluates and compares the effectiveness of future action and event prediction for three types of RL agents: explicitly planning, implicitly planning, and non-planning. We employ two approaches: the inner state approach, which involves predicting based on the inner computations of the agents (e.g., plans or neuron activations), and a simulation-based approach, which involves unrolling the agent in a learned world model. Our results show that the plans of explicitly planning agents are significantly more informative for prediction than the neuron activations of the other types. Furthermore, using internal plans proves more robust to model quality compared to simulation-based approaches when predicting actions, while the results for event prediction are more mixed. These findings highlight the benefits of leveraging inner states and simulations to predict future agent actions and events, thereby improving interaction and safety in real-world deployments.

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover diverse states. However, in complex environments with many state factors (e.g., household environments with many objects), learning skills that cover all possible states is impossible, and naively encouraging state diversity often leads to simple skills that are not ideal for solving downstream tasks. This work introduces Skill Discovery from Local Dependencies (Skild), which leverages state factorization as a natural inductive bias to guide the skill learning process. The key intuition guiding Skild is that skills that induce diverse interactions between state factors are often more valuable for solving downstream tasks. To this end, Skild develops a novel skill learning objective that explicitly encourages the mastering of skills that effectively induce different interactions within an environment. We evaluate Skild in several domains with challenging, long-horizon sparse reward tasks including a realistic simulated household robot domain, where Skild successfully learns skills with clear semantic meaning and shows superior performance compared to existing unsupervised reinforcement learning methods that only maximize state coverage.

Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) uses human preferences to achieve this alignment. However, preferences sourced from diverse populations can result in point estimates of human values that may be sub-optimal or unfair to specific groups. We propose Pareto Optimal Preference Learning (POPL), which frames discrepant group preferences as objectives with potential trade-offs, aiming for policies that are Pareto-optimal on the preference dataset. POPL utilizes Lexicase selection, an iterative process to select diverse and Pareto-optimal solutions. Our empirical evaluations demonstrate that POPL surpasses baseline methods in learning sets of reward functions, effectively catering to distinct groups without access to group numbers or membership labels. Furthermore, we illustrate that POPL can serve as a foundation for techniques optimizing specific notions of group fairness, ensuring inclusive and equitable AI model alignment.

Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs), however, it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained to represent human preferences, which is in turn used by an online reinforcement learning (RL) algorithm to optimize the LLM. A prominent issue with such methods is \emph{reward over-optimization} or \emph{reward hacking}, where performance as measured by the learned proxy reward model increases, but true quality plateaus or even deteriorates. Direct Alignment Algorithms (DDAs) like Direct Preference Optimization have emerged as alternatives to the classical RLHF pipeline by circumventing the reward modeling phase. However, although DAAs do not use a separate proxy reward model, they still commonly deteriorate from over-optimization. While the so-called reward hacking phenomenon is not well-defined for DAAs, we still uncover similar trends: at higher KL budgets, DAA algorithms exhibit similar degradation patterns to their classic RLHF counterparts. In particular, we find that DAA methods deteriorate not only across a wide range of KL budgets but also often before even a single epoch of the dataset is completed. Through extensive empirical experimentation, this work formulates and formalizes the reward over-optimization or hacking problem for DAAs and explores its consequences across objectives, training regimes, and model scales.

Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of tasks, we introduce a dynamic, interactive RL testbed based on robot air hockey. By augmenting air hockey with a large family of tasks ranging from easy tasks like reaching, to challenging ones like pushing a block by hitting it with a puck, as well as goal-based and human-interactive tasks, our testbed allows a varied assessment of RL capabilities. The robot air hockey testbed also supports sim-to-real transfer with three domains: two simulators of increasing fidelity and a real robot system. Using a dataset of demonstration data gathered through two teleoperation systems: a virtualized control environment, and human shadowing, we assess the testbed with behavior cloning, offline RL, and RL from scratch.

Varied approaches for aligning language models have been proposed, including supervised fine-tuning, RLHF, and direct optimization methods such as DPO. Although DPO has rapidly gained popularity due to its straightforward training process and competitive results, there is an open question of whether there remain practical advantages of using a discriminator, like a reward model, to evaluate responses. We propose D2PO, discriminator-guided DPO, an approach for the online setting where preferences are being collected throughout learning. As we collect gold preferences, we use these not only to train our policy, but to train a discriminative response evaluation model to silver-label even more synthetic data for policy training. We explore this approach across a set of diverse tasks, including a realistic chat setting, we find that our approach leads to higher-quality outputs compared to DPO with the same data budget, and greater efficiency in terms of preference data requirements. Furthermore, we show conditions under which silver labeling is most helpful: it is most effective when training the policy with DPO, outperforming traditional PPO, and benefits from maintaining a separate discriminator from the policy model.

Reinforcement learning (RL) algorithms often struggle to learn policies that generalize to novel situations due to issues such as causal confusion, overfitting to irrelevant factors, and failure to isolate control of state factors. These issues stem from a common source: a failure to accurately identify and exploit state-specific causal relationships in the environment. While some prior works in RL aim to identify these relationships explicitly, they rely on informal domain-specific heuristics such as spatial and temporal proximity. Actual causality offers a principled and general framework for determining the causes of particular events. However, existing definitions of actual cause often attribute causality to a large number of events, even if many of them rarely influence the outcome. Prior work on actual causality proposes normality as a solution to this problem, but its existing implementations are challenging to scale to complex and continuous-valued RL environments. This paper introduces functional actual cause (FAC), a framework that uses context-specific independencies in the environment to restrict the set of actual causes. We additionally introduce Joint Optimization for Actual Cause Inference (JACI), an algorithm that learns from observational data to infer functional actual causes. We demonstrate empirically that FAC agrees with known results on a suite of examples from the actual causality literature, and JACI identifies actual causes with significantly higher accuracy than existing heuristic methods in a set of complex, continuous-valued environments.