ترغب بنشر مسار تعليمي؟ اضغط هنا

Imitation-Projected Programmatic Reinforcement Learning

122   0   0.0 ( 0 )
 نشر من قبل Abhinav Verma
 تاريخ النشر 2019
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification than neural policies; however, designing rigorous learning approaches for such policies remains a challenge. Our approach to this challenge -- a meta-algorithm called PROPEL -- is based on three insights. First, we view our learning task as optimization in policy space, modulo the constraint that the desired policy has a programmatic representation, and solve this optimization problem using a form of mirror descent that takes a gradient step into the unconstrained policy space and then projects back onto the constrained space. Second, we view the unconstrained policy space as mixing neural and programmatic representations, which enables employing state-of-the-art deep policy gradient approaches. Third, we cast the projection step as program synthesis via imitation learning, and exploit contemporary combinatorial methods for this task. We present theoretical convergence results for PROPEL and empirically evaluate the approach in three continuous control domains. The experiments show that PROPEL can significantly outperform state-of-the-art approaches for learning programmatic policies.



قيم البحث

اقرأ أيضاً

The capability of reinforcement learning (RL) agent directly depends on the diversity of learning scenarios the environment generates and how closely it captures real-world situations. However, existing environments/simulators lack the support to sys tematically model distributions over initial states and transition dynamics. Furthermore, in complex domains such as soccer, the space of possible scenarios is infinite, which makes it impossible for one research group to provide a comprehensive set of scenarios to train, test, and benchmark RL algorithms. To address this issue, for the first time, we adopt an existing formal scenario specification language, SCENIC, to intuitively model and generate interactive scenarios. We interfaced SCENIC to Google Research Soccer environment to create a platform called SCENIC4RL. Using this platform, we provide a dataset consisting of 36 scenario programs encoded in SCENIC and demonstration data generated from a subset of them. We share our experimental results to show the effectiveness of our dataset and the platform to train, test, and benchmark RL algorithms. More importantly, we open-source our platform to enable RL community to collectively contribute to constructing a comprehensive set of scenarios.
We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent policies. Unlike the popular Deep Reinforcement Learning (DRL) paradig m, which represents policies by neural networks, PIRL represents policies using a high-level, domain-specific programming language. Such programmatic policies have the benefits of being more easily interpreted than neural networks, and being amenable to verification by symbolic methods. We propose a new method, called Neurally Directed Program Search (NDPS), for solving the challenging nonsmooth optimization problem of finding a programmatic policy with maximal reward. NDPS works by first learning a neural policy network using DRL, and then performing a local search over programmatic policies that seeks to minimize a distance from this neural oracle. We evaluate NDPS on the task of learning to drive a simulated car in the TORCS car-racing environment. We demonstrate that NDPS is able to discover human-readable policies that pass some significant performance bars. We also show that PIRL policies can have smoother trajectories, and can be more easily transferred to environments not encountered during training, than corresponding policies discovered by DRL.
385 - Eiji Uchibe , Kenji Doya 2020
This paper proposes Entropy-Regularized Imitation Learning (ERIL), which is a combination of forward and inverse reinforcement learning under the framework of the entropy-regularized Markov decision process. ERIL minimizes the reverse Kullback-Leible r (KL) divergence between two probability distributions induced by a learner and an expert. Inverse reinforcement learning (RL) in ERIL evaluates the log-ratio between two distributions using the density ratio trick, which is widely used in generative adversarial networks. More specifically, the log-ratio is estimated by building two binary discriminators. The first discriminator is a state-only function, and it tries to distinguish the state generated by the forward RL step from the experts state. The second discriminator is a function of current state, action, and transitioned state, and it distinguishes the generated experiences from the ones provided by the expert. Since the second discriminator has the same hyperparameters of the forward RL step, it can be used to control the discriminators ability. The forward RL minimizes the reverse KL estimated by the inverse RL. We show that minimizing the reverse KL divergence is equivalent to finding an optimal policy under entropy regularization. Consequently, a new policy is derived from an algorithm that resembles Dynamic Policy Programming and Soft Actor-Critic. Our experimental results on MuJoCo-simulated environments show that ERIL is more sample-efficient than such previous methods. We further apply the method to human behaviors in performing a pole-balancing task and show that the estimated reward functions show how every subject achieves the goal.
We present a training pipeline for the autonomous driving task given the current camera image and vehicle speed as the input to produce the throttle, brake, and steering control output. The simulator Airsims convenient weather and lighting API provid es a sufficient diversity during training which can be very helpful to increase the trained policys robustness. In order to not limit the possible policys performance, we use a continuous and deterministic control policy setting. We utilize ResNet-34 as our actor and critic networks with some slight changes in the fully connected layers. Considering humans mastery of this task and the high-complexity nature of this task, we first use imitation learning to mimic the given human policy and leverage the trained policy and its weights to the reinforcement learning phase for which we use DDPG. This combination shows a considerable performance boost comparing to both pure imitation learning and pure DDPG for the autonomous driving task.
Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach. Here, we cons ider a benchmark planning problem from the reinforcement learning domain, the Racetrack, to investigate the properties of agents derived from different deep (reinforcement) learning approaches. We compare the performance of deep supervised learning, in particular imitation learning, to reinforcement learning for the Racetrack model. We find that imitation learning yields agents that follow more risky paths. In contrast, the decisions of deep reinforcement learning are more foresighted, i.e., avoid states in which fatal decisions are more likely. Our evaluations show that for this sequential decision making problem, deep reinforcement learning performs best in many aspects even though for imitation learning optimal decisions are considered.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا