Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward function that encodes the entire task. Furthermore, the user often needs to manually shape the reward to ensure convergence of the learning algorithm. We propose a language for specifying complex control tasks, along with an algorithm that compiles specifications in our language into a reward function and automatically performs reward shaping. We implement our approach in a tool called SPECTRL, and show that it outperforms several state-of-the-art baselines.
Istituto Italiano di Tecnologia（意大利技术研究院）；Università di Genova（热那亚大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
A common strategy to deal with the expensive reinforcement learning (RL) of complex tasks is to decompose them into a collection of subtasks that are usually simpler to learn as well as reusable for new problems. However, when a robot learns the policies for these subtasks, common approaches treat every policy learning process separately. Therefore, all these individual (composable) policies need to be learned before tackling the learning process of the complex task through policies composition. Moreover, such composition of individual policies is usually performed sequentially, which is not s…
Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world robotic tasks. In this paper, we study how maximum entropy policies trained using soft Q-learning can be applied to real-world robotic manipulation. The application of this method to real-world manipulation is facilitated by two important features of soft Q-learning. First, soft Q-…
TU Darmstadt（达姆施塔特工业大学）；University of Washington（华盛顿大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Reactive motion generation problems are usually solved by computing actions as a sum of policies. However, these policies are independent of each other and thus, they can have conflicting behaviors when summing their contributions together. We introduce Composable Energy Policies (CEP), a novel framework for modular reactive motion generation. CEP computes the control action by optimization over the product of a set of stochastic policies. This product of policies will provide a high probability to those actions that satisfy all the components and low probability to the others. Optimizing over…
Resource-disaggregated data centre architectures promise a means of pooling resources remotely within data centres, allowing for both more flexibility and resource efficiency underlying the increasingly important infrastructure-as-a-service business. This can be accomplished by means of using an optically circuit switched backbone in the data centre network (DCN); providing the required bandwidth and latency guarantees to ensure reliable performance when applications are run across non-local resource pools. However, resource allocation in this scenario requires both server-level \emph{and} net…
parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning
Xinjiang Key Laboratory of Intelligent Computing and Smart Applications（新疆智能计算与智能应用重点实验室）；School of Software, Xinjiang University, Urumqi, China（新疆大学软件学院，中国乌鲁木齐）；School of Computing Science, Waseda University, Tokyo, Japan（早稻田大学计算机科学系，日本东京）
Brigham Young University（杨百翰大学）；University of Southern California（南加利福尼亚大学）
It is notoriously difficult to control the behavior of reinforcement learning agents. Agents often learn to exploit the environment or reward signal and need to be retrained multiple times. The multi-objective reinforcement learning (MORL) framework separates a reward function into several objectives. An ideal MORL agent learns to generalize to novel combinations of objectives allowing for better control of an agent's behavior without requiring retraining. Many MORL approaches use a weight vector to parameterize the importance of each objective. However, this approach suffers from lack of expr…
In this work we investigate on the concept of "restraining bolt", envisioned in Science Fiction. Specifically we introduce a novel problem in AI. We have two distinct sets of features extracted from the world, one by the agent and one by the authority imposing restraining specifications (the "restraining bolt"). The two sets are apparently unrelated since of interest to independent parties, however they both account for (aspects of) the same world. We consider the case in which the agent is a reinforcement learning agent on the first set of features, while the restraining bolt is specified log…
We study the problem of learning control policies for complex tasks given by logical specifications. Recent approaches automatically generate a reward function from a given specification and use a suitable reinforcement learning algorithm to learn a policy that maximizes the expected reward. These approaches, however, scale poorly to complex tasks that require high-level planning. In this work, we develop a compositional learning approach, called DiRL, that interleaves high-level planning and reinforcement learning. First, DiRL encodes the specification as an abstract graph; intuitively, verti…
Duke University（杜克大学）；University of California San Diego（加州大学圣地亚哥分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Probabilistic Computation Tree Logic (PCTL) is frequently used to formally specify control objectives such as probabilistic reachability and safety. In this work, we focus on model checking PCTL specifications statistically on Markov Decision Processes (MDPs) by sampling, e.g., checking whether there exists a feasible policy such that the probability of reaching certain goal states is greater than a threshold. We use reinforcement learning to search for such a feasible policy for PCTL specifications, and then develop a statistical model checking (SMC) method with provable guarantees on its err…
We report a bio-inspired framework for training a neural network through reinforcement learning to induce high level functions within the network. Based on the interpretation that animals have gained their cognitive functions such as object recognition - without ever being specifically trained for - as a result of maximizing their fitness to the environment, we place our agent in an environment where developing certain functions may facilitate decision making. The experimental results show that high level functions, such as image classification and hidden variable estimation, can be naturally …
University of Pennsylvania（宾夕法尼亚大学）；U.S. Army Research Laboratory（美国陆军研究实验室）
We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space. We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function (NAF). This representation of the policy enables efficiently composing multiple learned models without additional training samples or interaction with the environment. We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner whi…
There have been many studies on automated test generation for mobile Graphical User Interface (GUI) applications. These studies successfully demonstrate how to detect fatal exceptions and achieve high code and activity coverage with fully automated test generation engines. However, it is unclear how many GUI functions these engines manage to test. Furthermore, these engines implement only implicit test oracles. We propose Fully Automated Reinforcement LEArning-Driven Specification-Based Test Generator for Android (FARLEAD-Android). FARLEAD-Android accepts a GUI-level formal specification as a …
While notable progress has been made in specifying and learning objectives for general cyber-physical systems, applying these methods to distributed multi-agent systems still pose significant challenges. Among these are the need to (a) craft specification primitives that allow expression and interplay of both local and global objectives, (b) tame explosion in the state and action spaces to enable effective learning, and (c) minimize coordination frequency and the set of engaged participants for global objectives. To address these challenges, we propose a novel specification framework that allo…
Design of Voltage-Controlled Oscillator (VCO) inductors is a laborious and time-consuming task that is conventionally done manually by human experts. In this paper, we propose a framework for automating the design of VCO inductors, using Reinforcement Learning (RL). We formulate the problem as a sequential procedure, where wire segments are drawn one after another, until a complete inductor is created. We then employ an RL agent to learn to draw inductors that meet certain target specifications. In light of the need to tweak the target specifications throughout the circuit design cycle, we als…
Berkeley AI Research (BAIR)（伯克利人工智能研究院（BAIR））；University of California, Berkeley（加州大学伯克利分校）
A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific policies and assume the reward function for each task is known a priori. We propose a framework that learns event cues from off-policy data, and can flexibly combine these event cues at test time to accomplish different tasks. These event cue labels are not assumed to be known a priori, but are instead labeled using learned models, such as computer vision detect…
We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure. We represent this temporal structure by a finite-state machine and construct an on-the-fly synchronised product with the MDP and the finite machine. The temporal structure acts as a guide for the RL agent within the product, where a modular Deep Deterministic Policy Gradient (DDPG) architecture is proposed to generate a low-level control policy. We evalua…
University of Oxford（牛津大学）；Monash University（莫纳什大学）
In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour. From a learning perspective these specifications provide a rich formal language with which to capture tasks or objectives, while from a logic and automated verification perspective the introduction of learning capabilities allows for practical applications in large, stochastic, unknown environments. The existing work in this area is, however, limited. Of the frameworks that consider full linear temporal logic or ha…
Reinforcement learning tasks are typically specified as Markov decision processes. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning objective. This lack of modularity can complicate generalization of the task specification, as well as obfuscate connections between different task settings, such as episodic and continuing. In this work, we introduce the RL task formalism, that provides a unification through simple constructs including a generalization to transition-based discounting. Through a series of examples, we de…
Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. We argue for distributing RL components in a composable way by adapting algorithms for top-down hierarchical control, thereby encapsulating parallelism and resource requirements within short-running compute tasks. We demonstrate the benefits of this principle through RLlib: a library that provides scalable software primitives for RL. These primitives enable a broad range of algorithms to be implemented with high pe…
Signal temporal logic (STL) is an expressive language to specify time-bound real-world robotic tasks and safety specifications. Recently, there has been an interest in learning optimal policies to satisfy STL specifications via reinforcement learning (RL). Learning to satisfy STL specifications often needs a sufficient length of state history to compute reward and the next action. The need for history results in exponential state-space growth for the learning problem. Thus the learning problem becomes computationally intractable for most real-world applications. In this paper, we propose a com…
Institut d’intelligence aritficielle du Québec (Mila)（魁北克人工智能研究所（Mila））；École Polytechnique de Montréal（蒙特利尔理工学院）；Ubisoft La Forge（育碧La Forge实验室）；Université de Montréal（蒙特利尔大学）；ServiceNow（ServiceNow公司）
The standard formulation of Reinforcement Learning lacks a practical way of specifying what are admissible and forbidden behaviors. Most often, practitioners go about the task of behavior specification by manually engineering the reward function, a counter-intuitive process that requires several iterations and is prone to reward hacking by the agent. In this work, we argue that constrained RL, which has almost exclusively been used for safe RL, also has the potential to significantly reduce the amount of work spent for reward specification in applied RL projects. To this end, we propose to spe…
In this paper, we use concepts from supervisory control theory of discrete event systems to propose a method to learn optimal control policies for a finite-state Markov Decision Process (MDP) in which (only) certain sequences of actions are deemed unsafe (respectively safe). We assume that the set of action sequences that are deemed unsafe and/or safe are given in terms of a finite-state automaton; and propose a supervisor that disables a subset of actions at every state of the MDP so that the constraints on action sequence are satisfied. Then we present a version of the Q-learning algorithm f…
Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents
Tufts University（塔夫茨大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Georgia Tech Research Institute（佐治亚理工学院研究所）；University of Colorado Boulder（科罗拉多大学博尔德分校）
This letter proposes a novel reinforcement learning method for the synthesis of a control policy satisfying a control specification described by a linear temporal logic formula. We assume that the controlled system is modeled by a Markov decision process (MDP). We convert the specification to a limit-deterministic generalized Büchi automaton (LDGBA) with several accepting sets that accepts all infinite sequences satisfying the formula. The LDGBA is augmented so that it explicitly records the previous visits to accepting sets. We take a product of the augmented LDGBA and the MDP, based on which…
In reinforcement learning, wrappers are universally used to transform the information that passes between a model and an environment. Despite their ubiquity, no library exists with reasonable implementations of all popular preprocessing methods. This leads to unnecessary bugs, code inefficiencies, and wasted developer time. Accordingly we introduce SuperSuit, a Python library that includes all popular wrappers, and wrappers that can easily apply lambda functions to the observations/actions/reward. It's compatible with the standard Gym environment specification, as well as the PettingZoo specif…
CSAIL, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）；Toyota Research Institute（丰田研究所）；MIT Lincoln Laboratory（麻省理工学院林肯实验室）
Learning composable policies for environments with complex rules and tasks is a challenging problem. We introduce a hierarchical reinforcement learning framework called the Logical Options Framework (LOF) that learns policies that are satisfying, optimal, and composable. LOF efficiently learns policies that satisfy tasks by representing the task as an automaton and integrating it into learning and planning. We provide and prove conditions under which LOF will learn satisfying, optimal policies. And lastly, we show how LOF's learned policies can be composed to satisfy unseen tasks with only 10-…
Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning (Extended Version)
DEIB, Politecnico di Milano（博洛尼亚工程学院，米兰理工大学）；Politecnico di Milano（米兰理工大学）；INESC-ID/Instituto Superior Técnico Universidade de Lisboa（里斯本大学超级学院/葡萄牙信息科学与技术研究所）；Dipartimento di Informatica Università degli Studi di Milano（米兰大学信息学院）
Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin（得克萨斯大学奥斯汀分校奥登计算工程与科学研究所）；Uppsala University（乌普萨拉大学）；The University of Texas at Austin（得克萨斯大学奥斯汀分校）
We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, are composed to achieve an overall task. The framework consists of a high-level model, represented as a parametric Markov decision process (pMDP) which is used to plan and to analyze compositions of subsystems, and of the collection of low-level subsystems themselves. By defining interfaces between the subsystems, the framework enables automatic decompositions of task specifications, e.g., reach a target set of states…
University of Oxford（牛津大学）；Microsoft Research（微软研究院）；Google（谷歌）；Deepmind（深度思维）
Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are trained to maximize the likelihood of known reference programs. While achieving impressive results, this strategy has two key limitations. First, it ignores Program Aliasing: the fact that many different programs may satisfy a given specification (especially with incomplete speci…
Techniques based on Reinforcement Learning (RL) are increasingly being used to design control policies for robotic systems. RL fundamentally relies on state-based reward functions to encode desired behavior of the robot and bad reward functions are prone to exploitation by the learning agent, leading to behavior that is undesirable in the best case and critically dangerous in the worst. On the other hand, designing good reward functions for complex tasks is a challenging problem. In this paper, we propose expressing desired high-level robot behavior using a formal specification language known …
The combination of Formal Methods with Reinforcement Learning (RL) has recently attracted interest as a way for single-agent RL to learn multiple-task specifications. In this paper we extend this convergence to multi-agent settings and formally define Extended Markov Games as a general mathematical model that allows multiple RL agents to concurrently learn various non-Markovian specifications. To introduce this new model we provide formal definitions and proofs as well as empirical tests of RL algorithms running on this framework. Specifically, we use our model to train two different logic-bas…
A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In industrial scenarios, a system's behavior also needs to be predictable and lie within defined ranges. To enable the agents to learn (how) to align with a given specification, this paper proposes to explicitly transfer functional and non-functional requirements into shaped rewards. Experiments are carried out on the smart factory, a multi-agent environment mod…
We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL) specification. We propose a method to effectively augment the MDP state space to capture the required state history and express the STL objective as a reachability objective. The planning problem can then be formulated as a finite-horizon constrained Markov decision process (CMDP). For a general finite horizon CMDP problem with unknown transition probability, we dev…
Reinforcement learning has been shown to be an effective strategy for automatically training policies for challenging control problems. Focusing on non-cooperative multi-agent systems, we propose a novel reinforcement learning framework for training joint policies that form a Nash equilibrium. In our approach, rather than providing low-level reward functions, the user provides high-level specifications that encode the objective of each agent. Then, guided by the structure of the specifications, our algorithm searches over policies to identify one that provably forms an $ε$-Nash equilibrium (wi…
We apply deep reinforcement learning (DRL) to design of a networked controller with network delays to complete a temporal control task that is described by a signal temporal logic (STL) formula. STL is useful to deal with a specification with a bounded time interval for a dynamical system. In general, an agent needs not only the current system state but also the past behavior of the system to determine a desired control action for satisfying the given STL formula. Additionally, we need to consider the effect of network delays for data transmissions. Thus, we propose an extended Markov decision…
MILA（蒙特利尔学习算法研究所）；McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）；Université de Montréal（蒙特利尔大学）
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the reward with external factors that are not known to the agent. Corruption or stochasticity of the reward signal can be especially problematic in robotics, where goal specification can be particularly difficult for complex tasks. While many variance reduction techniques have been stud…
Advances in deep learning have led to promising progress in inferring graphics programs by de-rendering computer-generated images. However, current methods do not explore which decoding methods lead to better inductive bias for inferring graphics programs. In our work, we first explore the effectiveness of LSTM-RNN versus Transformer networks as decoders for order-independent graphics programs. Since these are sequence models, we must choose an ordering of the objects in the graphics programs for likelihood training. We found that the LSTM performance was highly sensitive to the sequence order…
University of Colorado Boulder（科罗拉多大学博尔德分校）；Tata Institute of Fundamental Research（塔塔基础研究所）
Continuous-time Markov decision processes (CTMDPs) are canonical models to express sequential decision-making under dense-time and stochastic environments. When the stochastic evolution of the environment is only available via sampling, model-free reinforcement learning (RL) is the algorithm-of-choice to compute optimal decision sequence. RL, on the other hand, requires the learning objective to be encoded as scalar reward signals. Since doing such translations manually is both tedious and error-prone, a number of techniques have been proposed to translate high-level objectives (expressed in l…
