Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learning models, as other deep learning models, tend to be opaque in their decision-making process. In this work, we propose to make deep reinforcement learning more transparent by visualizing the evidence on which the agent bases its decision. In this work, we emphasize the importance of producing a justification for an observed action, which could be applied to a black-box decision 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 explo…
Google Brain（谷歌大脑）；Institute of Mathematics of the Polish Academy of Sciences（波兰科学院数学研究所）；Faculty of Mathematics, Informatics and Mechanics, University of Warsaw（华沙大学数学、信息学与力学学院）；University of Illinois at Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校）；Stanford University（斯坦福大学）
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts of data. Model-based techniques are more data-efficient, but need to acquire explicit knowledge about the environment. In this paper, we take a step towards using model-based techniques in environments with a high-dimensional visual state space by demonstrating t…
This paper explores the use of deep reinforcement learning agents to transfer knowledge from one environment to another. More specifically, the method takes advantage of asynchronous advantage actor critic (A3C) architecture to generalize a target game using an agent trained on a source game in Atari. Instead of fine-tuning a pre-trained model for the target game, we propose a learning approach to update the model using multiple agents trained in parallel with different representations of the target game. Visual mapping between video sequences of transfer pairs is used to derive new representa…
Currently, many applications in Machine Learning are based on define new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others causes an impact in how to computers can learning by himself with only information called rewards obtained from any action. There is a lot of algorithms modeled and implemented based on Deep Recurrent Q-Learning proposed by DeepMind used in AlphaZero and Go. In this document, We proposed Deep Recurrent Double Q-Learning that is an implementation of Deep Reinf…
Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 games. We identify three key challenges that any algorithm needs to master in order to perform well on all games: processing diverse reward distributions, reasoning over long time horizons, and exploring efficiently. In this paper, we propose an algorithm that addresses each of these challenges and is able to learn human-level policies on nearly all Atari games. A new transformed Bellman operator a…
Australian National University（澳大利亚国立大学）；Deepmind（深度思维）
The Arcade Learning Environment (ALE) has become an essential benchmark for assessing the performance of reinforcement learning algorithms. However, the computational cost of generating results on the entire 57-game dataset limits ALE's use and makes the reproducibility of many results infeasible. We propose a novel solution to this problem in the form of a principled methodology for selecting small but representative subsets of environments within a benchmark suite. We applied our method to identify a subset of five ALE games, called Atari-5, which produces 57-game median score estimates with…
The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations. However, given the fact that deep reinforcement learning often deals with interpreting visual information, a large part of the train and inference time is spent performing convolutions. In this work we present our results on learning strategies in Atari games using a Convolutional Neural Network, the Math Kernel Library and TensorFlow 0.11rc0 machine learning framework. We also analyze effects of asy…
To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games…
Google Brain（谷歌大脑）；University of Montreal (Mila)（蒙特利尔大学（米拉研究所））；CIFAR（加拿大高等研究院）
Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interference within an environment inhibits learning. We test this hypothesis through a large-scale empirical study in the Arcade Learning Environment (ALE) and, indeed, find supporting evidence. We show that interference causes performance to plateau; the network cannot train on segments beyond the plateau without degrading the policy used to reach there. By synthetically controlling for interference, we demonstrate performance boosts across architectures, lear…
Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed. While compressing deep neural networks has of late assumed great importance to overcome this drawback, little work has been done to address this problem in the context of reinforcement learning agents. This work aims at making first steps towards model compression in an RL agent. In particular, we compress networks to drastically reduce the number of parameters in them (to sizes less than 3% of their original size), further facilitated by ap…
Motivated by vision-based reinforcement learning (RL) problems, in particular Atari games from the recent benchmark Aracade Learning Environment (ALE), we consider spatio-temporal prediction problems where future (image-)frames are dependent on control variables or actions as well as previous frames. While not composed of natural scenes, frames in Atari games are high-dimensional in size, can involve tens of objects with one or more objects being controlled by the actions directly and many other objects being influenced indirectly, can involve entry and departure of objects, and can involve de…
This paper proposes new, end-to-end deep reinforcement learning algorithms for learning two-player zero-sum Markov games. Different from prior efforts on training agents to beat a fixed set of opponents, our objective is to find the Nash equilibrium policies that are free from exploitation by even the adversarial opponents. We propose (a) Nash-DQN algorithm, which integrates the deep learning techniques from single DQN into the classic Nash Q-learning algorithm for solving tabular Markov games; (b) Nash-DQN-Exploiter algorithm, which additionally adopts an exploiter to guide the exploration of…
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
Franklin & Marshall College（富兰克林与马歇尔学院）；University of Alberta（阿尔伯塔大学）
The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its promise was demonstrated in the Arcade Learning Environment (ALE), a challenging framework composed of dozens of Atari 2600 games used to evaluate general competency in AI. It achieved dramatically better results than earlier approaches, showing that its ability to learn good representations is quite robust and general. This paper attempts to understand the principles that underlie DQN's impressive performance and to be…
Syscon Australia Pty. Ltd.（Syscon澳大利亚私人有限公司）；University of Manchester（曼彻斯特大学）
Deep reinforcement learning (DRL) requires large samples and a long training time to operate optimally. Yet humans rarely require long periods training to perform well on novel tasks, such as computer games, once they are provided with an accurate program of instructions. We used perceptual control theory (PCT) to construct a simple closed-loop model which requires no training samples and training time within a video game study using the Arcade Learning Environment (ALE). The model was programmed to parse inputs from the environment into hierarchically organised perceptual signals, and it comp…
Reinforcement learning has achieved great success in many applications. However, sample efficiency remains a key challenge, with prominent methods requiring millions (or even billions) of environment steps to train. Recently, there has been significant progress in sample efficient image-based RL algorithms; however, consistent human-level performance on the Atari game benchmark remains an elusive goal. We propose a sample efficient model-based visual RL algorithm built on MuZero, which we name EfficientZero. Our method achieves 194.3% mean human performance and 109.0% median performance on the…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）
We present Deep Control - new ML architecture of cortico-striatal brain circuits, which use whole cortical column as a structural element, instead of a singe neuron. Based on this architecture, we present MARTI - new model of human brain, considering neocortex and basal ganglia. This model is de-signed to implement expedient behavior and is capable to learn and achieve goals in unknown environments. We introduce a novel surprise feeling mechanism, that significantly improves reinforcement learning process through inner rewards. We use OpenAI Gym environment to demonstrate MARTI learning on a s…
The Arcade Learning Environment (ALE) is a popular platform for evaluating reinforcement learning agents. Much of the appeal comes from the fact that Atari games demonstrate aspects of competency we expect from an intelligent agent and are not biased toward any particular solution approach. The challenge of the ALE includes (1) the representation learning problem of extracting pertinent information from raw pixels, and (2) the behavioural learning problem of leveraging complex, delayed associations between actions and rewards. Often, the research questions we are interested in pertain more to …
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；University of Memphis（孟菲斯大学）
Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks that can be solved by trained policy. It plays a dominant role among cutting-edge machine learning approaches using multi-layer Neural networks (NNs). At the same time, Deep RL suffers from high sensitivity to noisy, incomplete, and misleading input data. Following biological intuition, we involve Spiking Neural Networks (SNNs) to address some deficiencies of deep RL solutions. Previous studies in image classification domain demonstrated that standard NNs (with ReLU nonlinearity) trained using supervised learning can …
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究院）
One major barrier to applications of deep Reinforcement Learning (RL) both inside and outside of games is the lack of explainability. In this paper, we describe a lightweight and effective method to derive explanations for deep RL agents, which we evaluate in the Atari domain. Our method relies on a transformation of the pixel-based input of the RL agent to an interpretable, percept-like input representation. We then train a surrogate model, which is itself interpretable, to replicate the behavior of the target, deep RL agent. Our experiments demonstrate that we can learn an effective surrogat…
We introduce CuLE (CUDA Learning Environment), a CUDA port of the Atari Learning Environment (ALE) which is used for the development of deep reinforcement algorithms. CuLE overcomes many limitations of existing CPU-based emulators and scales naturally to multiple GPUs. It leverages GPU parallelization to run thousands of games simultaneously and it renders frames directly on the GPU, to avoid the bottleneck arising from the limited CPU-GPU communication bandwidth. CuLE generates up to 155M frames per hour on a single GPU, a finding previously achieved only through a cluster of CPUs. Beyond hig…
MIT（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Width-based planning has shown promising results on Atari 2600 games using pixel input, while using substantially fewer environment interactions than reinforcement learning. Recent width-based approaches have computed feature vectors for each screen using a hand designed feature set or a variational autoencoder trained on game screens (VAE-IW), and prune screens that do not have novel features during the search. We propose Olive (Online-VAE-IW), which updates the VAE features online using active learning to maximize the utility of screens observed during planning. Experimental results in 55 At…
MILA, Université de Montréal（蒙特利尔大学米拉研究所）；Google Brain（谷歌大脑）
Research on exploration in reinforcement learning, as applied to Atari 2600 game-playing, has emphasized tackling difficult exploration problems such as Montezuma's Revenge (Bellemare et al., 2016). Recently, bonus-based exploration methods, which explore by augmenting the environment reward, have reached above-human average performance on such domains. In this paper we reassess popular bonus-based exploration methods within a common evaluation framework. We combine Rainbow (Hessel et al., 2018) with different exploration bonuses and evaluate its performance on Montezuma's Revenge, Bellemare e…
Low precision networks in the reinforcement learning (RL) setting are relatively unexplored because of the limitations of binary activations for function approximation. Here, in the discrete action ATARI domain, we demonstrate, for the first time, that low precision policy distillation from a high precision network provides a principled, practical way to train an RL agent. As an application, on 10 different ATARI games, we demonstrate real-time end-to-end game playing on low-power neuromorphic hardware by converting a sequence of game frames into discrete actions.
eXascale Infolab（eXascale信息实验室）；University of Fribourg, Switzerland（瑞士弗里堡大学）；Game Innovation Lab（游戏创新实验室）；Tandon School of Engineering（坦登工程学院）；New York University, NY, USA（美国纽约大学）
Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based on it. By separating the image processing from decision-making, one could better understand the complexity of each task, as well as potentially find smaller policy representations that are easier for humans to understand and may generalize better. To this end, we propose a new method for learning policies and compact state representations separately but simul…
Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods require excessive computation and interaction with the environment, so enhancements on sample efficiency are required. The main reason for this requirement is that sparse and delayed rewards do not provide an effective supervision for representation learning of deep neural networks. In this study, Proximal Policy Optimization (PPO) algorithm is augmented with Generative Adversarial Networks (GANs) to increase the sample ef…
Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical in higher dimensions due to their reliance on enumerating the state-action space. Hence, exploration in complex domains is often performed with simple epsilon-greedy methods. In this paper, we consider the challenging Atari games domain, which requires processing raw pixel inputs and delayed rewards. We evaluate several more sophisticated exploration strategi…
In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the full quantile function for the state-action return distribution. By reparameterizing a distribution over the sample space, this yields an implicitly defined return distribution and gives rise to a large class of risk-sensitive policies. We demonstrate improved performance on the 57 Atari 2600 games in the ALE, and use our algorithm's implicitly defined dist…
Reinforcement learning has exceeded human-level performance in game playing AI with deep learning methods according to the experiments from DeepMind on Go and Atari games. Deep learning solves high dimension input problems which stop the development of reinforcement for many years. This study uses both two techniques to create several agents with different algorithms that successfully learn to play T-rex Runner. Deep Q network algorithm and three types of improvements are implemented to train the agent. The results from some of them are far from satisfactory but others are better than human ex…
National Unviersity of Singapore（新加坡国立大学）；The University of Queesland（昆士兰大学）
Deep reinforcement learning is successful in decision making for sophisticated games, such as Atari, Go, etc. However, real-world decision making often requires reasoning with partial information extracted from complex visual observations. This paper presents Discriminative Particle Filter Reinforcement Learning (DPFRL), a new reinforcement learning framework for complex partial observations. DPFRL encodes a differentiable particle filter in the neural network policy for explicit reasoning with partial observations over time. The particle filter maintains a belief using learned discriminative …
Deep reinforcement learning has become popular over recent years, showing superiority on different visual-input tasks such as playing Atari games and robot navigation. Although objects are important image elements, few work considers enhancing deep reinforcement learning with object characteristics. In this paper, we propose a novel method that can incorporate object recognition processing to deep reinforcement learning models. This approach can be adapted to any existing deep reinforcement learning frameworks. State-of-the-art results are shown in experiments on Atari games. We also propose a…
Google Research（谷歌研究）；DeepMind（深度思维）；University of Toronto（多伦多大学）
Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-efficiency. While learning world models from image inputs has recently become feasible for some tasks, modeling Atari games accurately enough to derive successful behaviors has remained an open challenge for many years. We introduce DreamerV2, a reinforcement learning agent that learns behaviors purely from predictions in the compact latent space of a powerful world model. The worl…
We present Mask Atari, a new benchmark to help solve partially observable Markov decision process (POMDP) problems with Deep Reinforcement Learning (DRL)-based approaches. To achieve a simulation environment for the POMDP problems, Mask Atari is constructed based on Atari 2600 games with controllable, moveable, and learnable masks as the observation area for the target agent, especially with the active information gathering (AIG) setting in POMDPs. Given that one does not yet exist, Mask Atari provides a challenging, efficient benchmark for evaluating the methods that focus on the above proble…
Imperial College London（帝国理工学院）；Einstein Center for Neurosciences Berlin（柏林爱因斯坦神经科学中心）；Technical University Berlin（柏林工业大学）；MRC London Institute of Medical Sciences（英国医学研究委员会伦敦医学科学研究所）
From a young age humans learn to use grammatical principles to hierarchically combine words into sentences. Action grammars is the parallel idea, that there is an underlying set of rules (a "grammar") that govern how we hierarchically combine actions to form new, more complex actions. We introduce the Action Grammar Reinforcement Learning (AG-RL) framework which leverages the concept of action grammars to consistently improve the sample efficiency of Reinforcement Learning agents. AG-RL works by using a grammar inference algorithm to infer the "action grammar" of an agent midway through traini…
Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is a counterfactual, which deals with "what if?" scenarios. In this work, we introduce the concept of a counterfactual state to help humans gain a better understanding of what would need to change (minimally) in an Atari game image for the agent to choose a different action. We introduce a …
University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；Alibaba Group（阿里巴巴集团）
Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games. However, these methods suffer from high variances and high sample complexity. On the other hand, model-based reinforcement learning methods that learn the transition dynamics are more sample efficient, but they often suffer from the bias of the transition estimation. How to make use of both model-based and model-free learning is a central problem in reinforcement learning. In this paper, we present a new technique …
UC San Diego（加州大学圣迭戈分校）；Microsoft Research（微软研究院）；Tsinghua University（清华大学）
Distributional Reinforcement Learning (RL) differs from traditional RL in that, rather than the expectation of total returns, it estimates distributions and has achieved state-of-the-art performance on Atari Games. The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution. Existing distributional RL algorithms parameterize either the probability side or the return value side of the distribution function, leaving the other side uniformly fixed as in C51, QR-DQN or randomly sampled …
Despite the notable successes in video games such as Atari 2600, current AI is yet to defeat human champions in the domain of real-time strategy (RTS) games. One of the reasons is that an RTS game is a multi-agent game, in which single-agent reinforcement learning methods cannot simply be applied because the environment is not a stationary Markov Decision Process. In this paper, we present a first step toward finding a game-theoretic solution to RTS games by applying Neural Fictitious Self-Play (NFSP), a game-theoretic approach for finding Nash equilibria, to Mini-RTS, a small but nontrivial R…
Spiking neural networks (SNNs) have great potential for energy-efficient implementation of Deep Neural Networks (DNNs) on dedicated neuromorphic hardware. Recent studies demonstrated competitive performance of SNNs compared with DNNs on image classification tasks, including CIFAR-10 and ImageNet data. The present work focuses on using SNNs in combination with deep reinforcement learning in ATARI games, which involves additional complexity as compared to image classification. We review the theory of converting DNNs to SNNs and extending the conversion to Deep Q-Networks (DQNs). We propose a rob…
Deep reinforcement learning has achieved great successes in recent years, but there are still open challenges, such as convergence to locally optimal policies and sample inefficiency. In this paper, we contribute a novel self-supervised auxiliary task, i.e., Terminal Prediction (TP), estimating temporal closeness to terminal states for episodic tasks. The intuition is to help representation learning by letting the agent predict how close it is to a terminal state, while learning its control policy. Although TP could be integrated with multiple algorithms, this paper focuses on Asynchronous Adv…
Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason could be the lack of guarantees on the performance of the intermediate executed policies, compared to an existing (already working) baseline policy. In this paper, we propose an online model-free algorithm that solves conservative exploration in the policy optimization problem. We show that the regret of the proposed approach is bounded by $\tilde{\mathcal{O…
HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
Technical University of Darmstadt（达姆施塔特工业大学）；Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心）；Centre for Cognitive Science of Darmstadt（达姆施塔特认知科学中心）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
Samsung AI Center（三星人工智能中心）；Steklov Institute of Mathematics at St. Petersburg（圣彼得堡斯捷克洛夫数学研究所）；Neuromation OU（Neuromation公司）
We propose a new approach to visualize saliency maps for deep neural network models and apply it to deep reinforcement learning agents trained on Atari environments. Our method adds an attention module that we call FLS (Free Lunch Saliency) to the feature extractor from an established baseline (Mnih et al., 2015). This addition results in a trainable model that can produce saliency maps, i.e., visualizations of the importance of different parts of the input for the agent's current decision making. We show experimentally that a network with an FLS module exhibits performance similar to the base…
In the past few years, deep reinforcement learning has been proven to solve problems which have complex states like video games or board games. The next step of intelligent agents would be able to generalize between tasks, and using prior experience to pick up new skills more quickly. However, most reinforcement learning algorithms for now are often suffering from catastrophic forgetting even when facing a very similar target task. Our approach enables the agents to generalize knowledge from a single source task, and boost the learning progress with a semisupervised learning method when facing…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；CSAIL MIT（麻省理工学院计算机科学与人工智能实验室）
Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post-hoc for trained models or incorporated directly into the method itself (self-explaining). However, an overall selection does not properly capture the multi-faceted nature of useful rationales such as pros and cons for decisions. To this end, we propose a new game theoretic approach to class-dependent rationalization, where the method is specifically trained to highlight evidence supporting alternative conclusions. E…
Tel-Aviv University（特拉维夫大学）；Facebook AI Research（Facebook人工智能研究院）
In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another game? We attempt to answer this research question by creating visual analogies between a pair of games: a source game and a target game. For example, given a video frame in the target game, we map it to an analogous state in the source game and then attempt to play using a trained policy learned for the source game. We demonstrate convincing visual mapping between four pairs of …
In this paper we revisit the method of off-policy corrections for reinforcement learning (COP-TD) pioneered by Hallak et al. (2017). Under this method, online updates to the value function are reweighted to avoid divergence issues typical of off-policy learning. While Hallak et al.'s solution is appealing, it cannot easily be transferred to nonlinear function approximation. First, it requires a projection step onto the probability simplex; second, even though the operator describing the expected behavior of the off-policy learning algorithm is convergent, it is not known to be a contraction ma…
Saliency maps are frequently used to support explanations of the behavior of deep reinforcement learning (RL) agents. However, a review of how saliency maps are used in practice indicates that the derived explanations are often unfalsifiable and can be highly subjective. We introduce an empirical approach grounded in counterfactual reasoning to test the hypotheses generated from saliency maps and assess the degree to which they correspond to the semantics of RL environments. We use Atari games, a common benchmark for deep RL, to evaluate three types of saliency maps. Our results show the exten…
