An official website of the United States government
Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose RL-VLM-F, a method that automatically generates reward functions for agents to learn new tasks, using only a text description of the task goal and the agent's visual observations, by leveraging feedbacks from vision language foundation models (VLMs). The key to our approach is to query these models to give preferences over pairs of the agent's image observations based on the text description of the task goal, and then learn a reward function from the preference labels, rather than directly prompting these models to output a raw reward score, which can be noisy and inconsistent. We demonstrate that RL-VLM-F successfully produces effective rewards and policies across various domains - including classic control, as well as manipulation of rigid, articulated, and deformable objects - without the need for human supervision, outperforming prior methods that use large pretrained models for reward generation under the same assumptions.
more »
« less
This content will become publicly available on May 25, 2027
Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications
When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with human-provided specifications becomes critical for responsible AI deployment. Reward design provides a direct channel for such alignment by translating human expectations into reward functions that guide reinforcement learning (RL). However, existing methods are often too limited to capture nuanced human preferences that arise in long-horizon tasks. Hence, we introduce Hierarchical Reward Design from Language (HRDL): a problem formulation that extends classical reward design to encode richer behavioral specifications for hierarchical RL agents. We further propose Language to Hierarchical Rewards (L2HR) as a solution to HRDL. Experiments show that AI agents trained with rewards designed via L2HR not only complete tasks effectively but also better adhere to human specifications. Together, HRDL and L2HR advance the research on human-aligned AI agents.
more »
« less
- Award ID(s):
- 2205454
- PAR ID:
- 10667008
- Publisher / Repository:
- International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
- Date Published:
- Edition / Version:
- 25
- Subject(s) / Keyword(s):
- Reward Design Hierarchical Reinforcement Learning Human-Centered AI
- Format(s):
- Medium: X
- Location:
- Paphos, Cyprus
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recent reinforcement learning (RL) approaches have shown strong performance in complex domains such as Atari games, but are often highly sample inefficient. A common approach to reduce interaction time with the environment is to use reward shaping, which involves carefully designing reward functions that provide the agent intermediate rewards for progress towards the goal. However, designing appropriate shaping rewards is known to be difficult as well as time-consuming. In this work, we address this problem by using natural language instructions to perform reward shaping. We propose the LanguagE-Action Reward Network (LEARN), a framework that maps free-form natural language instructions to intermediate rewards based on actions taken by the agent. These intermediate language-based rewards can seamlessly be integrated into any standard reinforcement learning algorithm. We experiment with Montezuma’s Revenge from the Atari Learning Environment, a popular benchmark in RL. Our experiments on a diverse set of 15 tasks demonstrate that, for the same number of interactions with the environment, language-based rewards lead to successful completion of the task 60 % more often on average, compared to learning without language.more » « less
-
Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for capturing human intent to alleviate the challenges of hand-crafting the reward values. Despite the increasing interest in RLHF, most works learn black box reward functions that while expressive are difficult to interpret and often require running the whole costly process of RL before we can even decipher if these frameworks are actually aligned with human preferences. We propose and evaluate a novel approach for learning expressive and interpretable reward functions from preferences using Differentiable Decision Trees (DDTs). Our experiments across several domains, including CartPole, Visual Gridworld environments and Atari games, provide evidence that the tree structure of our learned reward function is useful in determining the extent to which the reward function is aligned with human preferences. We also provide experimental evidence that not only shows that reward DDTs can often achieve competitive RL performance when compared with larger capacity deep neural network reward functions but also demonstrates the diagnostic utility of our framework in checking alignment of learned reward functions. We also observe that the choice between soft and hard (argmax) output of reward DDT reveals a tension between wanting highly shaped rewards to ensure good RL performance, while also wanting simpler, more interpretable rewards. Videos and code, are available at: https://sites.google.com/view/ddt-rlhfmore » « less
-
Recent advances in reinforcement learning (RL) have renewed focus on the design of reward functions that shape agent behavior. Manually crafting such functions is often tedious and error-prone. A more principled alternative is to specify behavioral requirements using a formal, unambiguous language that can be automatically translated into a reward function. Omega-regular languages are a natural choice for this purpose, given their established role in formal verification and synthesis. However, existing approaches using omega-regular specifications typically rely on discounted reward RL in an episodic setting, where the environment is periodically reset to an initial state during learning. This setup is misaligned with the semantics of omega-regular specifications, which describe properties over infinite behavior traces. In such cases, the average reward criterion and the continuing setting—where the agent interacts with the environment over a single, uninterrupted lifetime—are more appropriate.To address the challenges of infinite-horizon, continuing tasks, we restrict our focus to the subclass of omega-regular languages known as absolute liveness specifications. These specifications cannot be violated by any finite prefix of the agent’s behavior, aligning naturally with the continuing setting. We present the first model-free RL framework that translates absolute liveness specifications to average-reward objectives. In contrast to prior work, our approach enables learning in communicating Markov Decision Processes without episodic resetting. We further introduce a reward structure for lexicographic multi-objective optimization, where the goal is to maximize an external average-reward objective among the policies that also maximize the satisfaction probability of a given absolute liveness omega-regular specification. Our method guarantees convergence in unknown communicating MDPs and supports on-the-fly reductions that do not require full knowledge of the environment, thus enabling model-free RL. Empirical results across various benchmarks demonstrate that our average-reward approach in the continuing setting is more effective than competing methods based on discounting.more » « less
-
null (Ed.)Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-policy learning. Specifically, we learn a reward model by actively querying a teacher’s preferences between two clips of behavior and use it to train an agent. To enable off-policy learning, we relabel all the agent’s past experience when its reward model changes. We additionally show that pre-training our agents with unsupervised exploration substantially increases the mileage of its queries. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods, including a variety of locomotion and robotic manipulation skills. We also show that our method is able to utilize real-time human feedback to effectively prevent reward exploitation and learn new behaviors that are difficult to specify with standard reward functions.more » « less
