Related papers: An Oracle and Observations for the OpenAI Gym / AL…
Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…
Simulation plays a crucial role in the rapid development and safe deployment of autonomous vehicles. Realistic traffic agent models are indispensable for bridging the gap between simulation and the real world. Many existing approaches for…
Securing coordination between AI agent and teammates (human players or AI agents) in contexts involving unfamiliar humans continues to pose a significant challenge in Zero-Shot Coordination. The issue of cooperative incompatibility becomes…
We propose to build a reinforcement learning prover of independent components: a deductive system (an environment), the proof state representation (how an agent sees the environment), and an agent training algorithm. To that purpose, we…
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration,…
Classical reinforcement learning (RL) has generated excellent results in different regions; however, its sample inefficiency remains a critical issue. In this paper, we provide concrete numerical evidence that the sample efficiency (the…
Real-time control is an essential aspect of safe robot operation in the real world with dynamic objects. We present a framework for the analysis of object-aware controllers, methods for altering a robot's motion to anticipate and avoid…
The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen…
We present a novel algorithm for game-theoretic trajectory planning, tailored for settings in which agents can only observe one another in specific regions of the state space. Such problems arise naturally in the context of multi-robot…
The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and…
Developing agents capable of autonomously interacting with complex and dynamic environments, where task structures may change over time and prior knowledge cannot be relied upon, is a key prerequisite for deploying artificial systems in…
Inspired by recent developments in attention models for image classification and natural language processing, we present various Attention based architectures in reinforcement learning (RL) domain, capable of performing well on OpenAI Gym…
Reinforcement learning usually makes use of numerical rewards, which have nice properties but also come with drawbacks and difficulties. Using rewards on an ordinal scale (ordinal rewards) is an alternative to numerical rewards that has…
Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We…
Offline Reinforcement Learning (ORL) offers a robust solution to training agents in applications where interactions with the environment must be strictly limited due to cost, safety, or lack of accurate simulation environments. Despite its…
Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult…
We interpret solving the multi-vehicle routing problem as a team Markov game with partially observable costs. For a given set of customers to serve, the playing agents (vehicles) have the common goal to determine the team-optimal agent…
As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being…
Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the…
Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, handling the DevOps…