Evolution gave rise to human and animal intelligence here on Earth. We argue that the path to developing artificial human-like-intelligence will pass through mimicking the evolutionary process in a nature-like simulation. In Nature, there are two processes driving the development of the brain: evolution and learning. Evolution acts slowly, across generations, and amongst other things, it defines what agents learn by changing their internal reward function. Learning acts fast, across one's lifetime, and it quickly updates agents' policy to maximise pleasure and minimise pain. The reward function is slowly aligned with the fitness function by evolution, however, as agents evolve the environment and its fitness function also change, increasing the misalignment between reward and fitness. It is extremely computationally expensive to replicate these two processes in simulation. This work proposes Evolution via Evolutionary Reward (EvER) that allows learning to single-handedly drive the search for policies with increasingly evolutionary fitness by ensuring the alignment of the reward function with the fitness function. In this search, EvER makes use of the whole state-action trajectories that agents go through their lifetime. In contrast, current evolutionary algorithms discard this information and consequently limit their potential efficiency at tackling sequential decision problems. We test our algorithm in two simple bio-inspired environments and show its superiority at generating more capable agents at surviving and reproducing their genes when compared with a state-of-the-art evolutionary algorithm.

In the context of the ongoing Covid-19 pandemic, several reports and studies have attempted to model and predict the spread of the disease. There is also intense debate about policies for limiting the damage, both to health and to the economy. On the one hand, the health and safety of the population is the principal consideration for most countries. On the other hand, we cannot ignore the potential for long-term economic damage caused by strict nation-wide lockdowns. In this working paper, we present a quantitative way to compute lockdown decisions for individual cities or regions, while balancing health and economic considerations. Furthermore, these policies are \textit{learnt} automatically by the proposed algorithm, as a function of disease parameters (infectiousness, gestation period, duration of symptoms, probability of death) and population characteristics (density, movement propensity). We account for realistic considerations such as imperfect lockdowns, and show that the policy obtained using reinforcement learning is a viable quantitative approach towards lockdowns.

The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for 2-player video game AI. The challenge arises from the large action space, diverse styles of characters and abilities, and the real-time nature of the game. In this paper, we propose a novel algorithm that combines Rolling Horizon Evolution Algorithm (RHEA) with opponent model learning. The approach is readily applicable to any 2-player video game. In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent. The model is learned during the live gameplay. With the learned opponent model, the extended RHEA is able to make more realistic plans based on what the opponent is likely to do. This tends to lead to better results. We compared our approach directly with the bots from the FTGAIC 2018 competition, and found our method to significantly outperform all of them, for all three character. Furthermore, our proposed bot with the policy-gradient-based opponent model is the only one without using Monte-Carlo Tree Search (MCTS) among top five bots in the 2019 competition in which it achieved second place, while using much less domain knowledge than the winner.

As the Agent interacts with the Environment, it learns a policy. A policy is a "learned strategy" that governs the agents' behaviour in selecting an action at a particular time t of the Environment. A policy can be seen as a mapping from states of an Environment to the actions taken in those states. The goal of the reinforcement Agent is to maximize its long-term rewards as it interacts with the Environment in the feedback configuration. The response the Agent gets from each state-action cycle (where an Agent selects an action from a set of actions at each state of the Environment) is called the reward function. The reward function (or simply rewards) is a signal of the desirability of that state based on the action made by the Agent.

Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algorithms. Previous work has achieved good average performance by doing outstandingly well on many games of the set, but very poorly in several of the most challenging games. We propose Agent57, the first deep RL agent that outperforms the standard human benchmark on all 57 Atari games. To achieve this result, we train a neural network which parameterizes a family of policies ranging from very exploratory to purely exploitative. We propose an adaptive mechanism to choose which policy to prioritize throughout the training process. Additionally, we utilize a novel parameterization of the architecture that allows for more consistent and stable learning.

This paper presents a novel model-reference reinforcement learning control method for uncertain autonomous surface vehicles. The proposed control combines a conventional control method with deep reinforcement learning. With the conventional control, we can ensure the learning-based control law provides closed-loop stability for the overall system, and potentially increase the sample efficiency of the deep reinforcement learning. With the reinforcement learning, we can directly learn a control law to compensate for modeling uncertainties. In the proposed control, a nominal system is employed for the design of a baseline control law using a conventional control approach. The nominal system also defines the desired performance for uncertain autonomous vehicles to follow. In comparison with traditional deep reinforcement learning methods, our proposed learning-based control can provide stability guarantees and better sample efficiency. We demonstrate the performance of the new algorithm via extensive simulation results.

Epidemics of infectious diseases are an important threat to public health and global economies. Yet, the development of prevention strategies remains a challenging process, as epidemics are non-linear and complex processes. For this reason, we investigate a deep reinforcement learning approach to automatically learn prevention strategies in the context of pandemic influenza. Firstly, we construct a new epidemiological meta-population model, with 379 patches (one for each administrative district in Great Britain), that adequately captures the infection process of pandemic influenza. Our model balances complexity and computational efficiency such that the use of reinforcement learning techniques becomes attainable. Secondly, we set up a ground truth such that we can evaluate the performance of the 'Proximal Policy Optimization' algorithm to learn in a single district of this epidemiological model. Finally, we consider a large-scale problem, by conducting an experiment where we aim to learn a joint policy to control the districts in a community of 11 tightly coupled districts, for which no ground truth can be established. This experiment shows that deep reinforcement learning can be used to learn mitigation policies in complex epidemiological models with a large state space. Moreover, through this experiment, we demonstrate that there can be an advantage to consider collaboration between districts when designing prevention strategies.

Multi-task learning is a very challenging problem in reinforcement learning. While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It is unclear what parameters in the network should be reused across tasks, and the gradients from different tasks may interfere with each other. Thus, instead of naively sharing parameters across tasks, we introduce an explicit modularization technique on policy representation to alleviate this optimization issue. Given a base policy network, we design a routing network which estimates different routing strategies to reconfigure the base network for each task. Instead of creating a concrete route for each task, our task-specific policy is represented by a soft combination of all possible routes. We name this approach soft modularization. We experiment with multiple robotics manipulation tasks in simulation and show our method improves sample efficiency and performance over baselines by a large margin.

Overestimation of the maximum action-value is a well-known problem that hinders Q-Learning performance, leading to suboptimal policies and unstable learning. Among several Q-Learning variants proposed to address this issue, Weighted Q-Learning (WQL) effectively reduces the bias and shows remarkable results in stochastic environments. WQL uses a weighted sum of the estimated action-values, where the weights correspond to the probability of each action-value being the maximum; however, the computation of these probabilities is only practical in the tabular settings. In this work, we provide the methodological advances to benefit from the WQL properties in Deep Reinforcement Learning (DRL), by using neural networks with Dropout Variational Inference as an effective approximation of deep Gaussian processes. In particular, we adopt the Concrete Dropout variant to obtain calibrated estimates of epistemic uncertainty in DRL. We show that model uncertainty in DRL can be useful not only for action selection, but also action evaluation. We analyze how the novel Weighted Deep Q-Learning algorithm reduces the bias w.r.t. relevant baselines and provide empirical evidence of its advantages on several representative benchmarks.

For all lectures, slides, and lab materials: http://introtodeeplearning.com