Intelligent agents, such as robots, are increasingly deployed in real-world, human-centric environments. To foster appropriate human trust and meet legal and ethical standards, these agents must be able to explain their behavior. However, state-of-the-art agents are typically driven by black-box models like deep neural networks, limiting their interpretability. We propose a method for generating natural language explanations of agent behavior based only on observed states and actions -- without access to the agent's underlying model. Our approach learns a locally interpretable surrogate model of the agent's behavior from observations, which then guides a large language model to generate plausible explanations with minimal hallucination. Empirical results show that our method produces explanations that are more comprehensible and correct than those from baselines, as judged by both language models and human evaluators. Furthermore, we find that participants in a user study more accurately predicted the agent's future actions when given our explanations, suggesting improved understanding of agent behavior.

We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. It provides explicit near-optimal policies for any reward specified a posteriori. During an unsupervised phase, we use rewardfree interactions with the environment to learn two representations via off-the-shelf deep learning methods and temporal difference (TD) learning. In the test phase, a reward representation is estimated either from reward observations or an explicit reward description (e.g., a target state). The optimal policy for that reward is directly obtained from these representations, with no planning.

We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. It provides explicit near-optimal policies for any reward specified a posteriori. During an unsupervised phase, we use rewardfree interactions with the environment to learn two representations via off-the-shelf deep learning methods and temporal difference (TD) learning. In the test phase, a reward representation is estimated either from reward observations or an explicit reward description (e.g., a target state). The optimal policy for that reward is directly obtained from these representations, with no planning.

Solutions to Markov Decision Processes (MDP) are often very sensitive to state transition probabilities. As the estimation of these probabilities is often inaccurate in practice, it is important to understand when and how Reinforcement Learning (RL) agents generalize when transition probabilities change. Here we present a new methodology to evaluate such generalization of RL agents under small shifts in the transition probabilities. Specifically, we evaluate agents in new environments (MDPs) in the vicinity of the training MDP created by adding quantifiable, parametric noise into the transition function of the training MDP. We refer to this process as Noise Injection, and the resulting environments as $\delta$-environments. This process allows us to create controlled variations of the same environment with the level of the noise serving as a metric of distance between environments. Conventional wisdom suggests that training and testing on the same MDP should yield the best results. However, we report several cases of the opposite -- when targeting a specific environment, training the agent in an alternative noise setting can yield superior outcomes. We showcase this phenomenon across $60$ different variations of ATARI games, including PacMan, Pong, and Breakout.

The ability to continuously learn and adapt to new situations is one where humans are far superior compared to AI agents. We propose an approach to knowledge transfer using behavioural strategies as a form of transferable knowledge influenced by the human cognitive ability to develop strategies. A strategy is defined as a partial sequence of events - where an event is both the result of an agent's action and changes in state - to reach some predefined event of interest. This information acts as guidance or a partial solution that an agent can generalise and use to make predictions about how to handle unknown observed phenomena. As a first step toward this goal, we develop a method for extracting strategies from an agent's existing knowledge that can be applied in multiple contexts. Our method combines observed event frequency information with local sequence alignment techniques to find patterns of significance that form a strategy. We show that our method can identify plausible strategies in three environments: Pacman, Bank Heist and a dungeon-crawling video game. Our evaluation serves as a promising first step toward extracting knowledge for generalisation and, ultimately, transfer learning.

Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such that an agent chooses a different action. Generating counterfactual explanations for RL agents with visual input is especially challenging because of their large state spaces and because their decisions are part of an overarching policy, which includes long-term decision-making. However, research focusing on counterfactual explanations, specifically for RL agents with visual input, is scarce and does not go beyond identifying defective agents. It is unclear whether counterfactual explanations are still helpful for more complex tasks like analyzing the learned strategies of different agents or choosing a fitting agent for a specific task. We propose a novel but simple method to generate counterfactual explanations for RL agents by formulating the problem as a domain transfer problem which allows the use of adversarial learning techniques like StarGAN. Our method is fully model-agnostic and we demonstrate that it outperforms the only previous method in several computational metrics. Furthermore, we show in a user study that our method performs best when analyzing which strategies different agents pursue.

The ultimate performance of machine learning algorithms for classification tasks is usually measured in terms of the empirical error probability (or accuracy) based on a testing dataset. Whereas, these algorithms are optimized through the minimization of a typically different--more convenient--loss function based on a training set. For classification tasks, this loss function is often the negative log-loss that leads to the well-known cross-entropy risk which is typically better behaved (from a numerical perspective) than the error probability. Conventional studies on the generalization error do not usually take into account the underlying mismatch between losses at training and testing phases. In this work, we introduce an analysis based on point-wise PAC approach over the generalization gap considering the mismatch of testing based on the accuracy metric and training on the negative log-loss. We label this analysis PACMAN. Building on the fact that the mentioned mismatch can be written as a likelihood ratio, concentration inequalities can be used to provide some insights for the generalization problem in terms of some point-wise PAC bounds depending on some meaningful information-theoretic quantities. An analysis of the obtained bounds and a comparison with available results in the literature are also provided.

Reinforcement learning has made great strides in recent years due to the success of methods using deep neural networks. However, such neural networks act as a black box, obscuring the inner workings. While reinforcement learning has the potential to solve unique problems, a lack of trust and understanding of reinforcement learning algorithms could prevent their widespread adoption. Here, we present a library that attaches a "data scraper" to deep reinforcement learning agents, acting as an observer, and then show how the data collected by the Atari Data Scraper can be used to understand and interpret deep reinforcement learning agents. The code for the Atari Data Scraper can be found here: https: // github.