11 accepted papers
Outside of transfer learning settings, reinforcement learning agents start their learning process from a clean slate. As a result, such agents have to go through a slow process to learn even the most obvious skills required to solve a problem. In this paper, we present InnateCoder, a system that lev
Cost-guided bottom-up search (BUS) algorithms use a cost function to guide the search to solve program synthesis tasks. In this paper, we show that current state-of-the-art cost-guided BUS algorithms suffer from a common problem: they can lose useful information given by the model and fail to perfor…
Syntax-guided synthesis is commonly used to generate programs encoding policies. In this approach, the set of programs, that can be written in a domain-specific language defines the search space, and an algorithm searches within this space for programs that encode strong policies. In this paper, we…
This paper introduces a local search method for improving an existing program with respect to a measurable objective. Program Optimization with Locally Improving Search (POLIS) exploits the structure of a program, defined by its lines. POLIS improves a single line of the program while keeping the re…
This paper introduces Local Learner (2L), an algorithm for providing a set of reference strategies to guide the search for programmatic strategies in two-player zero-sum games. Previous learning algorithms, such as Iterated Best Response (IBR), Fictitious Play (FP), and Double-Oracle (DO), can be co…
Levin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansions before reaching a goal node, depending on the quality of the policy. This guarantee can be used as a loss function…
In this paper we show that behavioral cloning can be used to learn effective sketches of programmatic strategies. We show that even the sketches learned by cloning the behavior of weak players can help the synthesis of programmatic strategies. This is because even weak players can provide helpful in…
AI-systems that model and interact with their users can up-date their models over time to reflect new information and changes in the environment. Although these updates may improve the overall performance of the AI-system, they may actually hurt the performance with respect to individual users. Prio…
The use of a policy and a heuristic function for guiding search can be quite effective in adversarial problems, as demonstrated by AlphaGo and its successors, which are based on the PUCT search algorithm. While PUCT can also be used to solve single-agent deterministic problems, it lacks guarantee…
Search-based systems have shown to be effective for planning in zero-sum games. However, search-based approaches have important disadvantages. First, the decisions of search algorithms are mostly non-interpretable, which is problematic in domains where predictability and trust are desired such as co…
In this paper we review several planning algorithms developed for zero-sum games with exponential action spaces, i.e., spaces that grow exponentially with the number of game components that can act simultaneously at a given game state. As an example, real-time strategy games have exponential action…