The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are distributed over time and potentially give better clues to policy improvement. Also, physical implementation of such policies, e.g. in robotics, is less problematic, as it avoids making robots shake. This is in opposition to most RL algorithms which add white noise to control causing unwanted shaking of the robots. An algorithm is introduced here that approximately optimizes the aforementioned policy. Its efficiency is verified for four simulated learning control problems (Ant, HalfCheetah, Hopper, and Walker2D) against three other methods (PPO, SAC, ACER). The algorithm outperforms others in three of these problems.

Reinforcement learning provides an appealing formalism for learning control policies from experience. However, the classic active formulation of reinforcement learning necessitates a lengthy active exploration process for each behavior, making it difficult to apply in real-world settings. If we can instead allow reinforcement learning to effectively use previously collected data to aid the online learning process, where the data could be expert demonstrations or more generally any prior experience, we could make reinforcement learning a substantially more practical tool. While a number of recent methods have sought to learn offline from previously collected data, it remains exceptionally difficult to train a policy with offline data and improve it further with online reinforcement learning. In this paper we systematically analyze why this problem is so challenging, and propose a novel algorithm that combines sample-efficient dynamic programming with maximum likelihood policy updates, providing a simple and effective framework that is able to leverage large amounts of offline data and then quickly perform online fine-tuning of reinforcement learning policies. We show that our method enables rapid learning of skills with a combination of prior demonstration data and online experience across a suite of difficult dexterous manipulation and benchmark tasks.

This work examines the use of reinforcement learning (RL) to optimize cyclic lockdowns, which is one of the methods available for control of the COVID-19 pandemic. The problem is structured as an optimal control system for tracking a reference value, corresponding to the maximum usage level of a critical resource, such as ICU beds. However, instead of using conventional optimal control methods, RL is used to find optimal control policies. A framework was developed to calculate optimal cyclic lockdown timings using an RL-based on-off controller. The RL-based controller is implemented as an RL agent that interacts with an epidemic simulator, implemented as an extended SEIR epidemic model. The RL agent learns a policy function that produces an optimal sequence of open/lockdown decisions such that goals specified in the RL reward function are optimized. Two concurrent goals were used: the first one is a public health goal that minimizes overshoots of ICU bed usage above an ICU bed threshold, and the second one is a socio-economic goal that minimizes the time spent under lockdowns. It is assumed that cyclic lockdowns are considered as a temporary alternative to extended lockdowns when a region faces imminent danger of overpassing resource capacity limits and when imposing an extended lockdown would cause severe social and economic consequences due to lack of necessary economic resources to support its affected population during an extended lockdown.

Training agents to autonomously learn how to use anthropomorphic robotic hands has the potential to lead to systems capable of performing a multitude of complex manipulation tasks in unstructured and uncertain environments. In this work, we first introduce a suite of challenging simulated manipulation tasks that current reinforcement learning and trajectory optimisation techniques find difficult. These include environments where two simulated hands have to pass or throw objects between each other, as well as an environment where the agent must learn to spin a long pen between its fingers. We then introduce a simple trajectory optimisation that performs significantly better than existing methods on these environments. Finally, on the challenging PenSpin task we combine sub-optimal demonstrations generated through trajectory optimisation with off-policy reinforcement learning, obtaining performance that far exceeds either of these approaches individually, effectively solving the environment.

Increasing response time of emergency vehicles (EVs) could lead to an immensurable loss of property and life. On this account, tactical decision making for EV's microscopic control remains an indispensable issue to be improved. Our approach verifies that deep reinforcement learning could complement rule-based methods in generalization. It reveals that deterministic avoidance strategy for common vehicles at a low speed benefits EVs a lot, nevertheless, when at a high velocity, DQN breaks the deadlock of reduced safe distance and brings boldness to EVs in lane changing. Besides, a novel DQN method with speed-adaptive compact state space (SC-DQN) is put forward to fit in EVs' high-speed feature and generalize in various road topologies. All Above is implemented in SUMO emulator, where common vehicles are modeled rule-based whereas EVs are intelligently controlled.

Reinforcement Learning (RL) can be used to fit a mapping from patient state to a medication regimen. Prior studies have used deterministic and value-based tabular learning to learn a propofol dose from an observed anesthetic state. Deep RL replaces the table with a deep neural network and has been used to learn medication regimens from registry databases. Here we perform the first application of deep RL to closed-loop control of anesthetic dosing in a simulated environment. We use the cross-entropy method to train a deep neural network to map an observed anesthetic state to a probability of infusing a fixed propofol dosage. During testing, we implement a deterministic policy that transforms the probability of infusion to a continuous infusion rate. The model is trained and tested on simulated pharmacokinetic/pharmacodynamic models with randomized parameters to ensure robustness to patient variability. The deep RL agent significantly outperformed a proportional-integral-derivative controller (median absolute performance error 1.7% +/- 0.6 and 3.4% +/- 1.2). Modeling continuous input variables instead of a table affords more robust pattern recognition and utilizes our prior domain knowledge. Deep RL learned a smooth policy with a natural interpretation to data scientists and anesthesia care providers alike.

We introduce Phasic Policy Gradient (PPG), a reinforcement learning framework which modifies traditional on-policy actor-critic methods by separating policy and value function training into distinct phases. In prior methods, one must choose between using a shared network or separate networks to represent the policy and value function. Using separate networks avoids interference between objectives, while using a shared network allows useful features to be shared. PPG is able to achieve the best of both worlds by splitting optimization into two phases, one that advances training and one that distills features. PPG also enables the value function to be more aggressively optimized with a higher level of sample reuse. Compared to PPO, we find that PPG significantly improves sample efficiency on the challenging Procgen Benchmark.

We present a novel approach (DyNODE) that captures the underlying dynamics of a system by incorporating control in a neural ordinary differential equation framework. We conduct a systematic evaluation and comparison of our method and standard neural network architectures for dynamics modeling. Our results indicate that a simple DyNODE architecture when combined with an actor-critic reinforcement learning (RL) algorithm that uses model predictions to improve the critic's target values, outperforms canonical neural networks, both in sample efficiency and predictive performance across a diverse range of continuous tasks that are frequently used to benchmark RL algorithms. This approach provides a new avenue for the development of models that are more suited to learn the evolution of dynamical systems, particularly useful in the context of model-based reinforcement learning. To assist related work, we have made code available at https://github.com/vmartinezalvarez/DyNODE .

State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations. This makes it hard to transfer their success to industrial control problems, where simulations are often very costly or do not exist, and exploring in the real environment can potentially lead to catastrophic events. Recently developed, model-free, offline algorithms, can learn from a single dataset by mitigating extrapolation error in value functions. However, the robustness of the training process is still comparatively low, a problem known from methods using value functions. To improve robustness and stability of the learning process, we use dynamics models to assess policy performance instead of value functions, resulting in MOOSE (MOdel-based Offline policy Search with Ensembles), an algorithm which ensures low model bias by keeping the policy within the support of the data. We compare MOOSE with state-of-the-art model-free, offline RL algorithms BEAR and BCQ on the Industrial Benchmark and Mujoco continuous control tasks in terms of robust performance, and find that MOOSE outperforms its model-free counterparts in almost all considered cases, often even by far.

Reinforcement learning– Defined as the training of machine learning models to make a sequence of decisions, by trial and error.