In this research, we extend the universal reinforcement learning (URL) agent models of artificial general intelligence to quantum environments. The utility function of a classical exploratory stochastic Knowledge Seeking Agent, KL-KSA, is generalized to distance measures from quantum information theory on density matrices. Quantum process tomography (QPT) algorithms form the tractable subset of programs for modeling environmental dynamics. The optimal QPT policy is selected based on a mutable cost function based on algorithmic complexity as well as computational resource complexity. Instead of Turing machines, we estimate the cost metrics on a high-level language to allow realistic experimentation. The entire agent design is encapsulated in a self-replicating quine which mutates the cost function based on the predictive value of the optimal policy choosing scheme. Thus, multiple agents with pareto-optimal QPT policies evolve using genetic programming, mimicking the development of physical theories each with different resource trade-offs. This formal framework is termed Quantum Knowledge Seeking Agent (QKSA). Despite its importance, few quantum reinforcement learning models exist in contrast to the current thrust in quantum machine learning. QKSA is the first proposal for a framework that resembles the classical URL models. Similar to how AIXI-tl is a resource-bounded active version of Solomonoff universal induction, QKSA is a resource-bounded participatory observer framework to the recently proposed algorithmic information-based reconstruction of quantum mechanics. QKSA can be applied for simulating and studying aspects of quantum information theory. Specifically, we demonstrate that it can be used to accelerate quantum variational algorithms which include tomographic reconstruction as its integral subroutine.

In this paper, pragmatic implementation of an indoor autonomous delivery system that exploits Reinforcement Learning algorithms for path planning and collision avoidance is audited. The proposed system is a cost-efficient approach that is implemented to facilitate a Raspberry Pi controlled four-wheel-drive non-holonomic robot map a grid. This approach computes and navigates the shortest path from a source key point to a destination key point to carry out the desired delivery. Q learning and Deep-Q learning are used to find the optimal path while avoiding collision with static obstacles. This work defines an approach to deploy these two algorithms on a robot. A novel algorithm to decode an array of directions into accurate movements in a certain action space is also proposed. The procedure followed to dispatch this system with the said requirements is described, ergo presenting our proof of concept for indoor autonomous delivery vehicles.

Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However, learning such risk measures requires significant interaction with the environment, resulting in excessive constraint violations during learning. Furthermore, these measures are not easily transferable to new environments. We cast safe exploration as an offline meta-RL problem, where the objective is to leverage examples of safe and unsafe behavior across a range of environments to quickly adapt learned risk measures to a new environment with previously unseen dynamics. We then propose MEta-learning for Safe Adaptation (MESA), an approach for meta-learning a risk measure for safe RL. Simulation experiments across 5 continuous control domains suggest that MESA can leverage offline data from a range of different environments to reduce constraint violations in unseen environments by up to a factor of 2 while maintaining task performance.

You need Python 3.6 or later to run the simulation. Please follow the two links below to install Unity-Gym and Stable-Baselines. Also, you can train it using your custom reinforcement learning algorithms by following the OpenAI gym structure (https://gym.openai.com/). The image below illustrates the target goal of the AIcar, where the car needs to explore all the trajectories to find the bridge first.

In recent years, computational tools based on reinforcement learning have achieved remarkable results in numerous tasks, including image classification and robotic object manipulation. Meanwhile, computer scientists have also been training reinforcement learning models to play specific human games and videogames. To challenge research teams working on reinforcement learning techniques, the Neural Information Processing Systems (NeurIPS) annual conference introduced the MineRL competition, a contest in which different algorithms are tested on the same task in Minecraft, the renowned computer game developed by Mojang Studios. More specifically, contestants are asked to create algorithms that will need to obtain a diamond from raw pixels in the Minecraft game. The algorithms can only be trained for four days and on 8,000,000 samples created by the MineRL simulator, using a single GPU machine.

As with many other machine learning, or more generally, AI problems, RL can also be intimidating if one starts directly from the full problem and the formal mathematical definitions, so let us start by loosely defining RL as a collection of both problems and representations, meaning that, we have both RL problems and RL methods to solve that class of problems. More formally, when we are working on a reinforcement learning problem, we are trying to map specific situations to an action or a set of actions, and each of those actions will have a consequence or a "reward" which can be either positive, neutral, or negative, in fact, this can simply be a real number. For example, let's say that we have a pet monkey called Marcel and that he has a set of toys that he loves to play with, and let's say that we want to teach Marcel to pee in the toilet as opposed to on the floor, so to incentivize Marcel too choose the right action, we'll give him a new toy every time he pees in the toilet ( 1 toy) and we'll remove a toy from his collection (-1 toy) every time he pees on the floor. In this case, hopefully, Marcel (we can call him the "agent"), will learn to select an "action" (pee on the floor vs pee in the toilet) whenever he finds himself in a given situation or "state" -- when he feels the need to pee -- in a way to maximize the number of toys, namely the rewards, by choosing the right actions at that state. Now, I want to emphasize that while this example does a decent job describing the general idea of a reinforcement learning problem, there are many elements missing to fully describe the RL problem.

Games have a long history of serving as a benchmark for progress in artificial intelligence. Recently, approaches using search and learning have shown strong performance across a set of perfect information games, and approaches using game-theoretic reasoning and learning have shown strong performance for specific imperfect information poker variants. We introduce Player of Games, a general-purpose algorithm that unifies previous approaches, combining guided search, self-play learning, and game-theoretic reasoning. Player of Games is the first algorithm to achieve strong empirical performance in large perfect and imperfect information games -- an important step towards truly general algorithms for arbitrary environments. We prove that Player of Games is sound, converging to perfect play as available computation time and approximation capacity increases. Player of Games reaches strong performance in chess and Go, beats the strongest openly available agent in heads-up no-limit Texas hold'em poker (Slumbot), and defeats the state-of-the-art agent in Scotland Yard, an imperfect information game that illustrates the value of guided search, learning, and game-theoretic reasoning.

Temporal abstraction in reinforcement learning (RL), offers the promise of improving generalization and knowledge transfer in complex environments, by propagating information more efficiently over time. Although option learning was initially formulated in a way that allows updating many options simultaneously, using off-policy, intra-option learning (Sutton, Precup & Singh, 1999), many of the recent hierarchical reinforcement learning approaches only update a single option at a time: the option currently executing. We revisit and extend intra-option learning in the context of deep reinforcement learning, in order to enable updating all options consistent with current primitive action choices, without introducing any additional estimates. Our method can therefore be naturally adopted in most hierarchical RL frameworks. When we combine our approach with the option-critic algorithm for option discovery, we obtain significant improvements in performance and data-efficiency across a wide variety of domains.

Obtaining first-order regret bounds -- regret bounds scaling not as the worst-case but with some measure of the performance of the optimal policy on a given instance -- is a core question in sequential decision-making. While such bounds exist in many settings, they have proven elusive in reinforcement learning with large state spaces. In this work we address this gap, and show that it is possible to obtain regret scaling as $\mathcal{O}(\sqrt{V_1^\star K})$ in reinforcement learning with large state spaces, namely the linear MDP setting. Here $V_1^\star$ is the value of the optimal policy and $K$ is the number of episodes. We demonstrate that existing techniques based on least squares estimation are insufficient to obtain this result, and instead develop a novel robust self-normalized concentration bound based on the robust Catoni mean estimator, which may be of independent interest.

Real-world tasks of interest are generally poorly defined by human-readable descriptions and have no pre-defined reward signals unless it is defined by a human designer. Conversely, data-driven algorithms are often designed to solve a specific, narrowly defined, task with performance metrics that drives the agent's learning. In this work, we present the solution that won first place and was awarded the most human-like agent in the 2021 NeurIPS Competition MineRL BASALT Challenge: Learning from Human Feedback in Minecraft, which challenged participants to use human data to solve four tasks defined only by a natural language description and no reward function. Our approach uses the available human demonstration data to train an imitation learning policy for navigation and additional human feedback to train an image classifier. These modules, together with an estimated odometry map, are then combined into a state-machine designed based on human knowledge of the tasks that breaks them down in a natural hierarchy and controls which macro behavior the learning agent should follow at any instant. We compare this hybrid intelligence approach to both end-to-end machine learning and pure engineered solutions, which are then judged by human evaluators.