We are excited to present our work, combining the power of a symbolic approach and Large Language Models (LLMs). Our Symbolic API bridges the gap between classical programming (Software 1.0) and differentiable programming (Software 2.0). Conceptually, our framework uses neural networks - specifically LLMs - at its core, and composes operations based on task-specific zero-shot or few-shot prompting. We adopt a divide and conquer approach to decompose a complex problem into smaller problems. Therefore, each operation solves a simple task. By re-combining these operations, we can solve the complex problem. Furthermore, we demonstrate how to combine the strengths of both neural networks and symbolic reasoning to create AI systems that can solve a wide range of hard tasks. This includes fact-based generation of text, flow control of a generative process towards a desired outcome, and interpretability within generative processes.

Abstract

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the strategy to compute several models using different hyper-parameters, and, to subsequently compute a linear aggregation of the models. While several heuristics exist that follow this strategy, methods are still missing that rely on thorough theories for bounding the target error. In this turn, we propose a method that extends weighted least squares to vector-valued functions, e.g., deep neural networks. We show that the target error of the proposed algorithm is asymptotically not worse than twice the error of the unknown optimal aggregation. We also perform a large scale empirical comparative study on several datasets, including text, images, electroencephalogram, body sensor signals and signals from mobile phones. Our method outperforms deep embedded validation (DEV) and importance weighted validation (IWV) on all datasets, setting a new state-of-the-art performance for solving parameter choice issues in unsupervised domain adaptation with theoretical error guarantees. We further study several competitive heuristics, all outperforming IWV and DEV on at least five datasets. However, our method outperforms each heuristic on at least five of seven datasets.

Abstract

In lifelong learning, an agent learns throughout its entire life without resets, in a constantly changing environment, as we humans do. Consequently, lifelong learning comes with a plethora of research problems such as continual domain shifts, which result in non-stationary rewards and environment dynamics. These non-stationarities are difficult to detect and cope with due to their continuous nature. Therefore, exploration strategies and learning methods are required that are capable of tracking the steady domain shifts, and adapting to them. We propose Reactive Exploration to track and react to continual domain shifts in lifelong reinforcement learning, and to update the policy correspondingly. To this end, we conduct experiments in order to investigate different exploration strategies. We empirically show that representatives of the policy-gradient family are better suited for lifelong learning, as they adapt more quickly to distribution shifts than Q-learning. Thereby, policy-gradient methods profit the most from Reactive Exploration and show good results in lifelong learning with continual domain shifts. Our code is available at: this https URL.

Abstract

The application of Reinforcement Learning (RL) in real world environments can be expensive or risky due to sub-optimal policies during training. In Offline RL, this problem is avoided since interactions with an environment are prohibited. Policies are learned from a given dataset, which solely determines their performance. Despite this fact, how dataset characteristics influence Offline RL algorithms is still hardly investigated. The dataset characteristics are determined by the behavioral policy that samples this dataset. Therefore, we define characteristics of behavioral policies as exploratory for yielding high expected information in their interaction with the Markov Decision Process (MDP) and as exploitative for having high expected return. We implement two corresponding empirical measures for the datasets sampled by the behavioral policy in deterministic MDPs. The first empirical measure SACo is defined by the normalized unique state-action pairs and captures exploration. The second empirical measure TQ is defined by the normalized average trajectory return and captures exploitation. Empirical evaluations show the effectiveness of TQ and SACo. In large-scale experiments using our proposed measures, we show that the unconstrained off-policy Deep Q-Network family requires datasets with high SACo to find a good policy. Furthermore, experiments show that policy constraint algorithms perform well on datasets with high TQ and SACo. Finally, the experiments show, that purely dataset-constrained Behavioral Cloning performs competitively to the best Offline RL algorithms for datasets with high TQ.

Abstract

Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage steps in the Q-function that are associated with accomplishing sub-tasks. However, often only few episodes with high rewards are available as demonstrations since current exploration strategies cannot discover them in reasonable time. In this work, we introduce Align-RUDDER, which utilizes a profile model for reward redistribution that is obtained from multiple sequence alignment of demonstrations. Consequently, Align-RUDDER employs reward redistribution effectively and, thereby, drastically improves learning on few demonstrations. Align-RUDDER outperforms competitors on complex artificial tasks with delayed rewards and few demonstrations. On the Minecraft ObtainDiamond task, Align-RUDDER is able to mine a diamond, though not frequently. Code is available at this https URL.

Abstract

We address the unsolved algorithm design problem of choosing a justified regularization parameter in unsupervised domain adaptation. This problem is intriguing as no labels are available in the target domain. Our approach starts with the observation that the widely-used method of minimizing the source error, penalized by a distance measure between source and target feature representations, shares characteristics with regularized ill-posed inverse problems. Regularization parameters in inverse problems are optimally chosen by the fundamental principle of balancing approximation and sampling errors. We use this principle to balance learning errors and domain distance in a target error bound. As a result, we obtain a theoretically justified rule for the choice of the regularization parameter. In contrast to the state of the art, our approach allows source and target distributions with disjoint supports. An empirical comparative study on benchmark datasets underpins the performance of our approach.

Abstract

In reinforcement learning, an agent interacts with an environment from which it receives rewards, that are then used to learn a task. However, it is often unclear what strategies or concepts the agent has learned to solve the task. Thus, interpretability of the agent’s behavior is an important aspect in practical applications, next to the agent’s performance at the task itself. However, with the increasing complexity of both tasks and agents, interpreting the agent’s behavior becomes much more difficult. Therefore, developing new interpretable RL agents is of high importance. To this end, we propose to use Align-RUDDER as an interpretability method for reinforcement learning. Align-RUDDER is a method based on the recently introduced RUDDER framework, which relies on contribution analysis of an LSTM model, to redistribute rewards to key events. From these key events a strategy can be derived, guiding the agent’s decisions in order to solve a certain task. More importantly, the key events are in general interpretable by humans, and are often sub-tasks; where solving these sub-tasks is crucial for solving the main task. Align-RUDDER enhances the RUDDER framework with methods from multiple sequence alignment (MSA) to identify key events from demonstration trajectories. MSA needs only a few trajectories in order to perform well, and is much better understood than deep learning models such as LSTMs. Consequently, strategies and concepts can be learned from a few expert demonstrations, where the expert can be a human or an agent trained by reinforcement learning. By substituting RUDDER’s LSTM with a profile model that is obtained from MSA of demonstration trajectories, we are able to interpret an agent at three stages: First, by extracting common strategies from demonstration trajectories with MSA. Second, by encoding the most prevalent strategy via the MSA profile model and therefore explaining the expert’s behavior. And third, by allowing the interpretation of an arbitrary agent’s behavior based on its demonstration trajectories.