Multi-step greedy policies have been extensively used in model-based Reinforcement Learning (RL) and in the case when a model of the environment is available (e.g., in the game of Go). In this work, we explore the benefits of multi-step greedy policies in model-free RL when employed in the framework of multi-step Dynamic Programming (DP): multi-step Policy and Value Iteration. These algorithms iteratively solve short-horizon decision problems and converge to the optimal solution of the original one. By using model-free algorithms as solvers of the short-horizon problems we derive fully model-free algorithms which are instances of the multi-step DP framework. As model-free algorithms are prone to instabilities w.r.t. the decision problem horizon, this simple approach can help in mitigating these instabilities and results in an improved model-free algorithms. We test this approach and show results on both discrete and continuous control problems.

Xinle Liang 1, Y ang Liu 1, Tianjian Chen 1, Ming Liu 2 and Qiang Y ang 1 Abstract -- Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles. This sequential process is extremely time-consuming and more importantly, knowledge from the fine-tuned model stays local and can not be reused or leveraged collaboratively. T o tackle this problem, we present an online federated RL transfer process for real-time knowledge extraction where all the participant agents make corresponding actions with the knowledge learned by others, even when they are acting in very different environments. T o validate the effectiveness of the proposed approach, we constructed a real-life collision avoidance system with Microsoft Airsim simulator and NVIDIA JetsonTX2 car agents, which cooperatively learn from scratch to avoid collisions in indoor environment with obstacle objects. We demonstrate that with the proposed framework, the simulator car agents can transfer knowledge to the RC cars in real-time, with 27% increase in the average distance with obstacles and 42% decrease in the collision counts. I. INTRODUCTION Recent Reinforcement Learning (RL) researches in autonomous robots have achieved significant performance improvement by employing distributed architecture for decentralized agents [1], [2], which is termed as Distributed Reinforcement Learning (DRL). However, most existing DRL frameworks consider only synchronous learning with a constant environment.

We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, $Q$-functions, and dynamics. We show, theoretically and empirically, that even for one-dimensional continuous state space, there are many MDPs whose optimal $Q$-functions and policies are much more complex than the dynamics. We hypothesize many real-world MDPs also have a similar property. For these MDPs, model-based planning is a favorable algorithm, because the resulting policies can approximate the optimal policy significantly better than a neural network parameterization can, and model-free or model-based policy optimization rely on policy parameterization. Motivated by the theory, we apply a simple multi-step model-based bootstrapping planner (BOOTS) to bootstrap a weak $Q$-function into a stronger policy. Empirical results show that applying BOOTS on top of model-based or model-free policy optimization algorithms at the test time improves the performance on MuJoCo benchmark tasks.

--Angry Birds is a popular video game in which the player is provided with a sequence of birds to shoot from a slingshot. The task of the game is to destroy all green pigs with maximum possible score. Angry Birds appears to be a difficult task to solve for artificially intelligent agents due to the sequential decision-making, non-deterministic game environment, enormous state and action spaces and requirement to differentiate between multiple birds, their abilities and optimum tapping times. We describe the application of Deep Reinforcement learning by implementing Double Dueling Deep Q-network to play Angry Birds game. One of our main goals was to build an agent that is able to compete with previous participants and humans on the first 21 levels. In order to do so, we have collected a dataset of game frames that we used to train our agent on. We evaluate our agent using results of the previous participants of AIBirds competition, results of volunteer human players and present the results of AIBirds 2018 competition. I NTRODUCTION Angry Birds has been one of the most popular video games for a period of several years. The main goal of the game is to kill all green pigs on the level together with applying as much damage as possible to the surrounding structures.

One of the primary challenges for the realization of near-term quantum computers has to do with their most basic constituent: the qubit. Qubits can interact with anything in close proximity that carries energy close to their own--stray photons (i.e., unwanted electromagnetic fields), phonons (mechanical oscillations of the quantum device), or quantum defects (irregularities in the substrate of the chip formed during manufacturing)--which can unpredictably change the state of the qubits themselves. Further complicating matters, there are numerous challenges posed by the tools used to control qubits. Manipulating and reading out qubits is performed via classical controls: analog signals in the form of electromagnetic fields coupled to a physical substrate in which the qubit is embedded, e.g., superconducting circuits. Imperfections in these control electronics (giving rise to white noise), interference from external sources of radiation, and fluctuations in digital-to-analog converters, introduce even more stochastic errors that degrade the performance of quantum circuits.

Colibri Digital is a technology consultancy company founded in 2015 by James Cross and Ingrid Funie. The company works to help its clients navigate the rapidly changing and complex world of emerging technologies, with deep expertise in areas such as big data, data science, Machine Learning, and cloud computing. Over the past few years, they have worked with some of the World's largest and most prestigious companies, including a tier 1 investment bank, a leading management consultancy group, and one of the World's most popular soft drinks companies, helping each of them to better make sense of its data, and process it in more intelligent ways. Jim DiLorenzo is a freelance programmer and reinforcement learning enthusiast. He graduated from Columbia University and is working on his Masters in Computer Science.

Imagine: in 2001 Steven Spielberg released his science fiction movie called "Artificial Intelligence". Artificial intelligence programming is one of the hottest topics in the tech world today, and many influencers, from late, great Stephen Hawking to increasingly popular Elon Musk, both embrace the achievements of AI projects and warn us about the possible implications. So how does this new technology influence the world around us? Should you be worried that some AI robot will steal your job any time soon? Both academic and industrial researchers have put a lot of effort into creating adaptable smart machines for all sorts of industrial processes. Many startups have caught the trend and are beginning to develop reinforcement learning algorithms for industrial robotics.

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be understood by humans. To demonstrate this, we introduce a simple environment that requires challenging coordination, based on the popular game Overcooked, and learn a simple model that mimics human play. We evaluate the performance of agents trained via self-play and population-based training. These agents perform very well when paired with themselves, but when paired with our human model, they are significantly worse than agents designed to play with the human model. An experiment with a planning algorithm yields the same conclusion, though only when the human-aware planner is given the exact human model that it is playing with. A user study with real humans shows this pattern as well, though less strongly. Qualitatively, we find that the gains come from having the agent adapt to the human's gameplay. Given this result, we suggest several approaches for designing agents that learn about humans in order to better coordinate with them. Code is available at https://github.com/HumanCompatibleAI/overcooked_ai.

We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller which first estimates the dynamics and the rewards from a batch data set, and then solves for the optimal policy with respect to the estimates. The attacker can modify the data set slightly before learning happens, and wants to force the learner into learning a target policy chosen by the attacker. We present a unified framework for solving batch policy poisoning attacks, and instantiate the attack on two standard victims: tabular certainty equivalence learner in reinforcement learning and linear quadratic regulator in control. We show that both instantiation result in a convex optimization problem on which global optimality is guaranteed, and provide analysis on attack feasibility and attack cost. Experiments show the effectiveness of policy poisoning attacks.

Reinforcement learning algorithms are known to be sample inefficient, and often performance on one task can be substantially improved by leveraging information (e.g., via pre-training) on other related tasks. In this work, we propose a technique to achieve such knowledge transfer in cases where agent trajectories contain sensitive or private information, such as in the healthcare domain. Our approach leverages a differentially private policy evaluation algorithm to initialize an actor-critic model and improve the effectiveness of learning in downstream tasks. We empirically show this technique increases sample efficiency in resource-constrained control problems while preserving the privacy of trajectories collected in an upstream task.