We address the long-horizon mapless navigation problem: enabling robots to traverse novel environments without relying on high-definition maps or precise waypoints that specify exactly where to navigate. Achieving this requires overcoming two major challenges -- learning robust, generalizable perceptual representations of the environment without pre-enumerating all possible navigation factors and forms of perceptual aliasing and utilizing these learned representations to plan human-aligned navigation paths. Existing solutions struggle to generalize due to their reliance on hand-curated object lists that overlook unforeseen factors, end-to-end learning of navigation features from scarce large-scale robot datasets, and handcrafted reward functions that scale poorly to diverse scenarios. To overcome these limitations, we propose CREStE, the first method that learns representations and rewards for addressing the full mapless navigation problem without relying on large-scale robot datasets or manually curated features. CREStE leverages visual foundation models trained on internet-scale data to learn continuous bird's-eye-view representations capturing elevation, semantics, and instance-level features. To utilize learned representations for planning, we propose a counterfactual-based loss and active learning procedure that focuses on the most salient perceptual cues by querying humans for counterfactual trajectory annotations in challenging scenes. We evaluate CREStE in kilometer-scale navigation tasks across six distinct urban environments. CREStE significantly outperforms all state-of-the-art approaches with 70% fewer human interventions per mission, including a 2-kilometer mission in an unseen environment with just 1 intervention; showcasing its robustness and effectiveness for long-horizon mapless navigation. For videos and additional materials, see https://amrl.cs.utexas.edu/creste .

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.

Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as "zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present \emph{Proto Successor Measure}: the basis set for all possible solutions of Reinforcement Learning in a dynamical system. We provably show that any possible policy can be represented using an affine combination of these policy independent basis functions. Given a reward function at test time, we simply need to find the right set of linear weights to combine these basis corresponding to the optimal policy. We derive a practical algorithm to learn these basis functions using only interaction data from the environment and show that our approach can produce the optimal policy at test time for any given reward function without additional environmental interactions. Project page: https://agarwalsiddhant10.github.io/projects/psm.html.

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.

Offline Goal-Conditioned Reinforcement Learning (GCRL) is tasked with learning to achieve multiple goals in an environment purely from offline datasets using sparse reward functions. Offline GCRL is pivotal for developing generalist agents capable of leveraging pre-existing datasets to learn diverse and reusable skills without hand-engineering reward functions. However, contemporary approaches to GCRL based on supervised learning and contrastive learning are often suboptimal in the offline setting. An alternative perspective on GCRL optimizes for occupancy matching, but necessitates learning a discriminator, which subsequently serves as a pseudo-reward for downstream RL. Inaccuracies in the learned discriminator can cascade, negatively influencing the resulting policy. We present a novel approach to GCRL under a new lens of mixture-distribution matching, leading to our discriminator-free method: SMORe. The key insight is combining the occupancy matching perspective of GCRL with a convex dual formulation to derive a learning objective that can better leverage suboptimal offline data. SMORe learns scores or unnormalized densities representing the importance of taking an action at a state for reaching a particular goal. SMORe is principled and our extensive experiments on the fully offline GCRL benchmark composed of robot manipulation and locomotion tasks, including high-dimensional observations, show that SMORe can outperform state-of-the-art baselines by a significant margin. Many subfields of machine learning such as vision and NLP have enjoyed great success by designing objectives to learn a general model from large and diverse datasets. In robot learning, offline interaction data has become more prominent in the recent past (Ebert et al., 2021), with the scale of the datasets growing consistently (Walke et al., 2023; Padalkar et al., 2023).

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second, align the model by optimizing the learned reward via reinforcement learning (RL). This paradigm assumes that human preferences are distributed according to reward, but recent work suggests that they instead follow the regret under the user's optimal policy. Thus, learning a reward function from feedback is not only based on a flawed assumption of human preference, but also leads to unwieldy optimization challenges that stem from policy gradients or bootstrapping in the RL phase. Because of these optimization challenges, contemporary RLHF methods restrict themselves to contextual bandit settings (e.g., as in large language models) or limit observation dimensionality (e.g., state-based robotics). We overcome these limitations by introducing a new family of algorithms for optimizing behavior from human feedback using the regret-based model of human preferences. Using the principle of maximum entropy, we derive Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions, circumventing the need for RL. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs. This enables CPL to elegantly scale to high-dimensional and sequential RLHF problems while being simpler than prior methods. As large pretrained models have become increasingly performant, the problem of aligning them with human preferences have risen to the forefront of research. This alignment is especially difficult when larger datasets inevitably include suboptimal behaviors. Reinforcement learning from human feedback (RLHF) has emerged as a popular solution to this problem. Using human preferences, RLHF techniques discriminate between desirable and undesirable behaviors with the goal of refining a learned policy. This paradigm has shown promising results when applied to finetuning large language models (LLMs) (Ouyang et al., 2022), improving image generation models (Lee et al., 2023), and adapting robot policies (Christiano et al., 2017) - all from suboptimal data. For most RLHF algorithms, this process includes two phases.

The goal of reinforcement learning (RL) is to maximize the expected cumulative return. It has been shown that this objective can be represented by an optimization problem of the state-action visitation distribution under linear constraints [52]. The dual problem of this formulation, which we refer to as dual RL, is unconstrained and easier to optimize. We show that several state-of-the-art off-policy deep reinforcement learning (RL) algorithms, under both online and offline, RL and imitation learning (IL) settings, can be viewed as dual RL approaches in a unified framework. This unification provides a common ground to study and identify the components that contribute to the success of these methods and also reveals the common shortcomings across methods with new insights for improvement. Our analysis shows that prior off-policy imitation learning methods are based on an unrealistic coverage assumption and are minimizing a particular f-divergence between the visitation distributions of the learned policy and the expert policy. We propose a new method using a simple modification to the dual RL framework that allows for performant imitation learning with arbitrary off-policy data to obtain near-expert performance, without learning a discriminator. Further, by framing a recent SOTA offline RL method XQL [23] in the dual RL framework, we propose alternative choices to replace the Gumbel regression loss, which achieve improved performance and resolve the training instability issue of XQL. Project code and details can be found at this hari-sikchi.github.io/dual-rl.

We propose a new framework for imitation learning - treating imitation as a two-player ranking-based Stackelberg game between a $\textit{policy}$ and a $\textit{reward}$ function. In this game, the reward agent learns to satisfy pairwise performance rankings within a set of policies, while the policy agent learns to maximize this reward. This game encompasses a large subset of both inverse reinforcement learning (IRL) methods and methods which learn from offline preferences. The Stackelberg game formulation allows us to use optimization methods that take the game structure into account, leading to more sample efficient and stable learning dynamics compared to existing IRL methods. We theoretically analyze the requirements of the loss function used for ranking policy performances to facilitate near-optimal imitation learning at equilibrium. We use insights from this analysis to further increase sample efficiency of the ranking game by using automatically generated rankings or with offline annotated rankings. Our experiments show that the proposed method achieves state-of-the-art sample efficiency and is able to solve previously unsolvable tasks in the Learning from Observation (LfO) setting.

Deploying Reinforcement Learning (RL) agents in the real-world require that the agents satisfy safety constraints. Current RL agents explore the environment without considering these constraints, which can lead to damage to the hardware or even other agents in the environment. We propose a new method, LBPO, that uses a Lyapunov-based barrier function to restrict the policy update to a safe set for each training iteration. Our method also allows the user to control the conservativeness of the agent with respect to the constraints in the environment. LBPO significantly outperforms state-of-the-art baselines in terms of the number of constraint violations during training while being competitive in terms of performance. Further, our analysis reveals that baselines like CPO and SDDPG rely mostly on backtracking to ensure safety rather than safe projection, which provides insight into why previous methods might not have effectively limit the number of constraint violations.