Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with $n$ time steps, a policy will make $n$ decisions on actions to take, many of which may appear non-intuitive to the observer. Moreover, it is not clear which of these decisions directly contribute towards achieving the reward and how significant is their contribution. Given a trained policy, we propose a black-box method based on counterfactual reasoning that estimates the causal effect that these decisions have on reward attainment and ranks the decisions according to this estimate. In this preliminary work, we compare our measure against an alternative, non-causal, ranking procedure, highlight the benefits of causality-based policy ranking, and discuss potential future work integrating causal algorithms into the interpretation of RL agent policies.

Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them more difficult to analyse and interpret. In a run with $n$ time steps, a policy will decide $n$ times on an action to take, even when only a tiny subset of these decisions deliver value over selecting a simple default action. Given a pre-trained policy, we propose a black-box method based on statistical fault localisation that ranks the states of the environment according to the importance of decisions made in those states. We evaluate our ranking method by creating new, simpler policies by pruning decisions identified as unimportant, and measure the impact on performance. Our experimental results on a diverse set of standard benchmarks (gridworld, CartPole, Atari games) show that in some cases less than half of the decisions made contribute to the expected reward. We furthermore show that the decisions made in the most frequently visited states are not the most important for the expected reward.

We present a new approach for predicting program properties from large codebases (aka "Big Code"). Our approach learns a probabilistic model from "Big Code" and uses this model to predict properties of new, unseen programs. The key idea of our work is to transform the program into a representation that allows us to formulate the problem of inferring program properties as structured prediction in machine learning. This enables us to leverage powerful probabilistic models such as Conditional Random Fields (CRFs) and perform joint prediction of program properties. As an example of our approach, we built a scalable prediction engine called JSNICE for solving two kinds of tasks in the context of JavaScript: predicting (syntactic) names of identifiers and predicting (semantic) type annotations of variables. Experimentally, JSNICE predicts correct names for 63% of name identifiers and its type annotation predictions are correct in 81% of cases. Since its public release at http://jsnice.org, JSNice has become a popular system with hundreds of thousands of uses. By formulating the problem of inferring program properties as structured prediction, our work opens up the possibility for a range of new "Big Code" applications such as de-obfuscators, decompilers, invariant generators, and others. Recent years have seen significant progress in the area of programming languages driven by advances in type systems, constraint solving, program analysis, and synthesis techniques. Fundamentally, these methods reason about each program in isolation and while powerful, the effectiveness of programming tools based on these techniques is approaching its inherent limits. Thus, a more disruptive change is needed if a significant improvement is to take place. At the same time, creating probabilistic models from large datasets (also called "Big Data") has transformed a number of areas such as natural language processing, computer vision, recommendation systems, and many others. However, despite the overwhelming success of "Big Data" in a variety of application domains, learning from large datasets of programs has previously not had tangible impact on programming tools. Yet, with the tremendous growth of publicly available source code in repositories such as GitHub4 and BitBucket2 (referred to as "Big Code" by a recent DARPA initiative11) comes the opportunity to create new kinds of programming tools based on probabilistic models of such data.

We report about the current state and designated features of the tool SeaLion, aimed to serve as an integrated development environment (IDE) for answer-set programming (ASP). A main goal of SeaLion is to provide a user-friendly environment for supporting a developer to write, evaluate, debug, and test answer-set programs. To this end, new support techniques have to be developed that suit the requirements of the answer-set semantics and meet the constraints of practical applicability. In this respect, SeaLion benefits from the research results of a project on methods and methodologies for answer-set program development in whose context SeaLion is realised. Currently, the tool provides source-code editors for the languages of Gringo and DLV that offer syntax highlighting, syntax checking, and a visual program outline. Further implemented features are support for external solvers and visualisation as well as visual editing of answer sets. SeaLion comes as a plugin of the popular Eclipse platform and provides itself interfaces for future extensions of the IDE.