Standard reinforcement learning (RL) algorithms assume that the observation of the next state comes instantaneously and at no cost. In a wide variety of sequential decision making tasks ranging from medical treatment to scientific discovery, however, multiple classes of state observations are possible, each of which has an associated cost. We propose the active measure RL framework (Amrl) as an initial solution to this problem where the agent learns to maximize the costed return, which we define as the discounted sum of rewards minus the sum of observation costs. Our empirical evaluation demonstrates that Amrl-Q agents are able to learn a policy and state estimator in parallel during online training. During training the agent naturally shifts from its reliance on costly measurements of the environment to its state estimator in order to increase its reward. It does this without harm to the learned policy. Our results show that the Amrl-Q agent learns at a rate similar to standard Q-learning and Dyna-Q. Critically, by utilizing an active strategy, Amrl-Q achieves a higher costed return.

Penetration testing is a security exercise aimed at assessing the security of a system by simulating attacks against it. So far, penetration testing has been carried out mainly by trained human attackers and its success critically depended on the available expertise. Automating this practice constitutes a non-trivial problem, as the range of actions that a human expert may attempts against a system and the range of knowledge she relies on to take her decisions are hard to capture. In this paper, we focus our attention on simplified penetration testing problems expressed in the form of capture the flag hacking challenges, and we apply reinforcement learning algorithms to try to solve them. In modelling these capture the flag competitions as reinforcement learning problems we highlight the specific challenges that characterize penetration testing. We observe these challenges experimentally across a set of varied simulations, and we study how different reinforcement learning techniques may help us addressing these challenges. In this way we show the feasibility of tackling penetration testing using reinforcement learning, and we highlight the challenges that must be taken into consideration, and possible directions to solve them.

Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. On the other hand, reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline, while requiring minimal interactions with the environment. This is achieved by leveraging uncertainty estimates to divide the space in regions where the given model-based policy is reliable, and regions where it may have flaws or not be well defined. In these uncertain regions, we show that a locally learned-policy can be used directly with raw sensory inputs. We test our algorithm, Guided Uncertainty-Aware Policy Optimization (GUAPO), on a real-world robot performing peg insertion. Videos are available at https://sites.google.com/view/guapo-rl

The random nature of traffic conditions on freeways can cause excessive congestions and irregularities in the traffic flow. Ramp metering is a proven effective method to maintain freeway efficiency under various traffic conditions. Creating a reliable and practical ramp metering algorithm that considers both critical traffic measures and historical data is still a challenging problem. In this study we use machine learning approaches to develop a novel real-time prediction model for ramp metering. We evaluate the potentials of our approach in providing promising results by comparing it with a baseline traffic-responsive ramp metering algorithm.

Interventions are central to causal learning and reasoning. Yet ultimately an intervention is an abstraction: an agent embedded in a physical environment (perhaps modeled as a Markov decision process) does not typically come equipped with the notion of an intervention -- its action space is typically ego-centric, without actions of the form `intervene on X'. Such a correspondence between ego-centric actions and interventions would be challenging to hard-code. It would instead be better if an agent learnt which sequence of actions allow it to make targeted manipulations of the environment, and learnt corresponding representations that permitted learning from observation. Here we show how a meta-learning approach can be used to perform causal learning in this challenging setting, where the action-space is not a set of interventions and the observation space is a high-dimensional space with a latent causal structure. A meta-reinforcement learning algorithm is used to learn relationships that transfer on observational causal learning tasks. This work shows how advances in deep reinforcement learning and meta-learning can provide intervention-centric causal learning in high-dimensional environments with a latent causal structure.

A chatbot that converses like a human should be goal-oriented (i.e., be purposeful in conversation), which is beyond language generation. However, existing dialogue systems often heavily rely on cumbersome hand-crafted rules or costly labelled datasets to reach the goals. In this paper, we propose Goal-oriented Chatbots (GoChat), a framework for end-to-end training chatbots to maximize the longterm return from offline multi-turn dialogue datasets. Our framework utilizes hierarchical reinforcement learning (HRL), where the high-level policy guides the conversation towards the final goal by determining some sub-goals, and the low-level policy fulfills the sub-goals by generating the corresponding utterance for response. In our experiments on a real-world dialogue dataset for anti-fraud in financial, our approach outperforms previous methods on both the quality of response generation as well as the success rate of accomplishing the goal.

One critical prerequisite for the deployment of reinforcement learning systems in the real world is the ability to reliably detect situations on which the agent was not trained. Such situations could lead to potential safety risks when wrong predictions lead to the execution of harmful actions. In this work, we propose PEOC, a new policy entropy based out-of-distribution classifier that reliably detects unencountered states in deep reinforcement learning. It is based on using the entropy of an agent's policy as the classification score of a one-class classifier. We evaluate our approach using a procedural environment generator. Results show that PEOC is highly competitive against state-of-the-art one-class classification algorithms on the evaluated environments. Furthermore, we present a structured process for benchmarking out-of-distribution classification in reinforcement learning.

Training deep reinforcement learning agents on environments with multiple levels / scenes / conditions from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to the real world [1,2]. While such a strategy is helpful with generalization, the use of multiple scenes significantly increases the variance of samples collected for policy gradient computations. Current methods continue to view this collection of scenes as a single Markov Decision Process (MDP) with a common value function; however, we argue that it is better to treat the collection as a single environment with multiple underlying MDPs. To this end, we propose a dynamic value estimation (DVE) technique for these multiple-MDP environments, motivated by the clustering effect observed in the value function distribution across different scenes. The resulting agent is able to learn a more accurate and scene-specific value function estimate (and hence the advantage function), leading to a lower sample variance. Our proposed approach is simple to accommodate with several existing implementations (like PPO, A3C) and results in consistent improvements for a range of ProcGen environments and the AI2-THOR framework based visual navigation task.

Transferring as fast as possible the functioning of our brain to artificial intelligence is an ambitious goal that would help advance the state of the art in AI and robotics. It is in this perspective that we propose to start from hypotheses derived from an empirical study in a human-robot interaction and to verify if they are validated in the same way for children as for a basic reinforcement learning algorithm. Thus, we check whether receiving help from an expert when solving a simple close-ended task (the Towers of Hano\"i) allows to accelerate or not the learning of this task, depending on whether the intervention is canonical or requested by the player. Our experiences have allowed us to conclude that, whether requested or not, a Q-learning algorithm benefits in the same way from expert help as children do.

We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Policy Optimization (TRPO). Specifically, we investigate the consequences of "code-level optimizations:" algorithm augmentations found only in implementations or described as auxiliary details to the core algorithm. Seemingly of secondary importance, such optimizations turn out to have a major impact on agent behavior. Our results show that they (a) are responsible for most of PPO's gain in cumulative reward over TRPO, and (b) fundamentally change how RL methods function. These insights show the difficulty and importance of attributing performance gains in deep reinforcement learning. Code for reproducing our results is available at https://github.com/MadryLab/implementation-matters .