PyTorchKR Papers

최신 논문

총 991편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1909.11939

MERL: Multi-Head Reinforcement Learning

A common challenge in reinforcement learning is how to convert the agent's interactions with an environment into fast and robust learning. For instance, earlier work makes use of domain knowledge to improve existing reinforcement learning algorithms in complex tasks. While promising, previously acquired knowledge is often costly and challenging to scale up. Instead, we decide to consider problem knowledge with signals from quantities relevant to solve any task, e.g., self-performance assessment and accurate expectations. $\mathcal{V}^{ex}$ is such a quantity. It is the fraction of variance explained by the value function $V$ and measures the discrepancy between $V$ and the returns. Taking advantage of $\mathcal{V}^{ex}$, we propose MERL, a general framework for structuring reinforcement learning by injecting problem knowledge into policy gradient updates. As a result, the agent is not only optimized for a reward but learns using problem-focused quantities provided by MERL, applicable out-of-the-box to any task. In this paper: (a) We introduce and define MERL, the multi-head reinforcement learning framework we use throughout this work. (b) We conduct experiments across a variety of standard benchmark environments, including 9 continuous control tasks, where results show improved performance. (c) We demonstrate that MERL also improves transfer learning on a set of challenging pixel-based tasks. (d) We ponder how MERL tackles the problem of reward sparsity and better conditions the feature space of reinforcement learning agents.

arXiv:1909.11639

ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots

ROBEL is an open-source platform of cost-effective robots designed for reinforcement learning in the real world. ROBEL introduces two robots, each aimed to accelerate reinforcement learning research in different task domains: D'Claw is a three-fingered hand robot that facilitates learning dexterous manipulation tasks, and D'Kitty is a four-legged robot that facilitates learning agile legged locomotion tasks. These low-cost, modular robots are easy to maintain and are robust enough to sustain on-hardware reinforcement learning from scratch with over 14000 training hours registered on them to date. To leverage this platform, we propose an extensible set of continuous control benchmark tasks for each robot. These tasks feature dense and sparse task objectives, and additionally introduce score metrics as hardware-safety. We provide benchmark scores on an initial set of tasks using a variety of learning-based methods. Furthermore, we show that these results can be replicated across copies of the robots located in different institutions. Code, documentation, design files, detailed assembly instructions, final policies, baseline details, task videos, and all supplementary materials required to reproduce the results are available at www.roboticsbenchmarks.org.

arXiv:1909.10549공식 코드 · Papers with Code

Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbitrary advantage estimators, which allows the control of the bias and variance of any-order derivatives when using function approximation. Furthermore, we propose a method to trade off bias and variance of higher order derivatives by discounting the impact of more distant causal dependencies. We demonstrate the correctness and utility of our objective in analytically tractable MDPs and in meta-reinforcement-learning for continuous control.

arXiv:1909.09314공식 코드 · Papers with Code

Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations, several major challenges remain. First, existing IRL methods learn reward functions from scratch, requiring large numbers of demonstrations to correctly infer the reward for each task the agent may need to perform. Second, existing methods typically assume homogeneous demonstrations for a single behavior or task, while in practice, it might be easier to collect datasets of heterogeneous but related behaviors. To this end, we propose a deep latent variable model that is capable of learning rewards from demonstrations of distinct but related tasks in an unsupervised way. Critically, our model can infer rewards for new, structurally-similar tasks from a single demonstration. Our experiments on multiple continuous control tasks demonstrate the effectiveness of our approach compared to state-of-the-art imitation and inverse reinforcement learning methods.

arXiv:1909.09282

How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning?

Deep Reinforcement Learning is a promising paradigm for robotic control which has been shown to be capable of learning policies for high-dimensional, continuous control of unmodeled systems. However, RoboticReinforcement Learning currently lacks clearly defined benchmark tasks, which makes it difficult for researchers to reproduce and compare against prior work. ``Reacher'' tasks, which are fundamental to robotic manipulation, are commonly used as benchmarks, but the lack of a formal specification elides details that are crucial to replication. In this paper we present a novel empirical analysis which shows that the unstated spatial constraints in commonly used implementations of Reacher tasks make it dramatically easier to learn a successful control policy with DeepDeterministic Policy Gradients (DDPG), a state-of-the-art Deep RL algorithm. Our analysis suggests that less constrained Reacher tasks are significantly more difficult to learn, and hence that existing de facto benchmarks are not representative of the difficulty of general robotic manipulation.

arXiv:1909.07543

Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning

Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure coverage of the policy space, yet learning a population with the "best" coverage is still an open problem. In this work, we present a novel approach to population-based RL in continuous control that leverages properties of normalizing flows to perform attractive and repulsive operations between current members of the population and previously observed policies. Empirical results on the MuJoCo suite demonstrate a high performance gain for our algorithm compared to prior work, including Soft-Actor Critic (SAC).

arXiv:1909.07373

Policy Prediction Network: Model-Free Behavior Policy with Model-Based Learning in Continuous Action Space

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample complexity and performance on continuous control problems in exchange for extra computation at training time but at no cost in computation at rollout time. Our approach integrates a mix between model-free and model-based reinforcement learning. Policy Prediction Network is the first to introduce implicit model-based learning to Policy Gradient algorithms for continuous action space and is made possible via the empirically justified clipping scheme. Our experiments are focused on the MuJoCo environments so that they can be compared with similar work done in this area.

arXiv:1909.06851

Biased Estimates of Advantages over Path Ensembles

The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path ensemble, which allows one to flexibly drive the learning process, towards or against risks. On top of this formulation, we systematically study the impacts of different methods for estimating advantages. Our findings reveal that biased estimates, when chosen appropriately, can result in significant benefits. In particular, for the environments with sparse rewards, optimistic estimates would lead to more efficient exploration of the policy space; while for those where individual actions can have critical impacts, conservative estimates are preferable. On various benchmarks, including MuJoCo continuous control, Terrain locomotion, Atari games, and sparse-reward environments, the proposed biased estimation schemes consistently demonstrate improvement over mainstream methods, not only accelerating the learning process but also obtaining substantial performance gains.

arXiv:1909.06769

VILD: Variational Imitation Learning with Diverse-quality Demonstrations

The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts and amateurs. IL in such situations can be challenging, especially when the level of demonstrators' expertise is unknown. We propose a new IL method called \underline{v}ariational \underline{i}mitation \underline{l}earning with \underline{d}iverse-quality demonstrations (VILD), where we explicitly model the level of demonstrators' expertise with a probabilistic graphical model and estimate it along with a reward function. We show that a naive approach to estimation is not suitable to large state and action spaces, and fix its issues by using a variational approach which can be easily implemented using existing reinforcement learning methods. Experiments on continuous-control benchmarks demonstrate that VILD outperforms state-of-the-art methods. Our work enables scalable and data-efficient IL under more realistic settings than before.

arXiv:1909.06710공식 코드 · Papers with Code

Driving in Dense Traffic with Model-Free Reinforcement Learning

Traditional planning and control methods could fail to find a feasible trajectory for an autonomous vehicle to execute amongst dense traffic on roads. This is because the obstacle-free volume in spacetime is very small in these scenarios for the vehicle to drive through. However, that does not mean the task is infeasible since human drivers are known to be able to drive amongst dense traffic by leveraging the cooperativeness of other drivers to open a gap. The traditional methods fail to take into account the fact that the actions taken by an agent affect the behaviour of other vehicles on the road. In this work, we rely on the ability of deep reinforcement learning to implicitly model such interactions and learn a continuous control policy over the action space of an autonomous vehicle. The application we consider requires our agent to negotiate and open a gap in the road in order to successfully merge or change lanes. Our policy learns to repeatedly probe into the target road lane while trying to find a safe spot to move in to. We compare against two model-predictive control-based algorithms and show that our policy outperforms them in simulation.

arXiv:1909.03939

Deterministic Value-Policy Gradients

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we consider the deterministic value gradients to improve the sample efficiency of deep reinforcement learning algorithms. Previous works consider deterministic value gradients with the finite horizon, but it is too myopic compared with infinite horizon. We firstly give a theoretical guarantee of the existence of the value gradients in this infinite setting. Based on this theoretical guarantee, we propose a class of the deterministic value gradient algorithm (DVG) with infinite horizon, and different rollout steps of the analytical gradients by the learned model trade off between the variance of the value gradients and the model bias. Furthermore, to better combine the model-based deterministic value gradient estimators with the model-free deterministic policy gradient estimator, we propose the deterministic value-policy gradient (DVPG) algorithm. We finally conduct extensive experiments comparing DVPG with state-of-the-art methods on several standard continuous control benchmarks. Results demonstrate that DVPG substantially outperforms other baselines.

arXiv:1909.01331

Generalization in Transfer Learning

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously unseen tasks. Generalization and overfitting in deep reinforcement learning are not commonly addressed in current transfer learning research. Conducting a comparative analysis without an intermediate regularization step results in underperforming benchmarks and inaccurate algorithm comparisons due to rudimentary assessments. In this study, we propose regularization techniques in deep reinforcement learning for continuous control through the application of sample elimination, early stopping and maximum entropy regularized adversarial learning. First, the importance of the inclusion of training iteration number to the hyperparameters in deep transfer reinforcement learning will be discussed. Because source task performance is not indicative of the generalization capacity of the algorithm, we start by acknowledging the training iteration number as a hyperparameter. In line with this, we introduce an additional step of resorting to earlier snapshots of policy parameters to prevent overfitting to the source task. Then, to generate robust policies, we discard the samples that lead to overfitting via a method we call strict clipping. Furthermore, we increase the generalization capacity in widely used transfer learning benchmarks by using maximum entropy regularization, different critic methods, and curriculum learning in an adversarial setup. Subsequently, we propose maximum entropy adversarial reinforcement learning to increase the domain randomization. Finally, we evaluate the robustness of these methods on simulated robots in target environments where the morphology of the robot, gravity, and tangential friction coefficient of the environment are altered.

arXiv:1908.09357공식 코드 · Papers with Code

Dynamics-aware Embeddings

In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling efficient policy learning. We demonstrate that our action embeddings alone improve the sample efficiency and peak performance of model-free RL on control from low-dimensional states. By combining state and action embeddings, we achieve efficient learning of high-quality policies on goal-conditioned continuous control from pixel observations in only 1-2 million environment steps.

arXiv:1908.06012

Model-based Lookahead Reinforcement Learning

Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of state-of-the-art Model-free Reinforcement Learning (MFRL) methods. We leverage the strengths of both realms and propose an approach that obtains high performance with a small amount of data. In particular, we combine MFRL and Model Predictive Control (MPC). While MFRL's strength in exploration allows us to train a better forward dynamics model for MPC, MPC improves the performance of the MFRL policy by sampling-based planning. The experimental results in standard continuous control benchmarks show that our approach can achieve MFRL`s level of performance while being as data-efficient as MBRL.

arXiv:1908.05256

Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach

Deep Reinforcement Learning (DRL) has become a powerful methodology to solve complex decision-making problems. However, DRL has several limitations when used in real-world problems (e.g., robotics applications). For instance, long training times are required and cannot be accelerated in contrast to simulated environments, and reward functions may be hard to specify/model and/or to compute. Moreover, the transfer of policies learned in a simulator to the real-world has limitations (reality gap). On the other hand, machine learning methods that rely on the transfer of human knowledge to an agent have shown to be time efficient for obtaining well performing policies and do not require a reward function. In this context, we analyze the use of human corrective feedback during task execution to learn policies with high-dimensional state spaces, by using the D-COACH framework, and we propose new variants of this framework. D-COACH is a Deep Learning based extension of COACH (COrrective Advice Communicated by Humans), where humans are able to shape policies through corrective advice. The enhanced version of D-COACH, which is proposed in this paper, largely reduces the time and effort of a human for training a policy. Experimental results validate the efficiency of the D-COACH framework in three different problems (simulated and with real robots), and show that its enhanced version reduces the human training effort considerably, and makes it feasible to learn policies within periods of time in which a DRL agent do not reach any improvement.

arXiv:1908.04696

Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics

Continuous control and planning remains a major challenge in robotics and machine learning. Neuroscience offers the possibility of learning from animal brains that implement highly successful controllers, but it is unclear how to relate an animal's behavior to control principles. Animals may not always act optimally from the perspective of an external observer, but may still act rationally: we hypothesize that animals choose actions with highest expected future subjective value according to their own internal model of the world. Their actions thus result from solving a different optimal control problem from those on which they are evaluated in neuroscience experiments. With this assumption, we propose a novel framework of model-based inverse rational control that learns the agent's internal model that best explains their actions in a task described as a partially observable Markov decision process (POMDP). In this approach we first learn optimal policies generalized over the entire model space of dynamics and subjective rewards, using an extended Kalman filter to represent the belief space, a neural network in the actor-critic framework to optimize the policy, and a simplified basis for the parameter space. We then compute the model that maximizes the likelihood of the experimentally observable data comprising the agent's sensory observations and chosen actions. Our proposed method is able to recover the true model of simulated agents within theoretical error bounds given by limited data. We illustrate this method by applying it to a complex naturalistic task currently used in neuroscience experiments. This approach provides a foundation for interpreting the behavioral and neural dynamics of highly adapted controllers in animal brains.

arXiv:1908.02269

Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning

In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint action space that grows exponentially with the number of agents. While the tractability of independent agent-wise exploration is appealing, this approach fails on tasks that require elaborate group strategies. We argue that coordinating the agents' policies can guide their exploration and we investigate techniques to promote such an inductive bias. We propose two policy regularization methods: TeamReg, which is based on inter-agent action predictability and CoachReg that relies on synchronized behavior selection. We evaluate each approach on four challenging continuous control tasks with sparse rewards that require varying levels of coordination as well as on the discrete action Google Research Football environment. Our experiments show improved performance across many cooperative multi-agent problems. Finally, we analyze the effects of our proposed methods on the policies that our agents learn and show that our methods successfully enforce the qualities that we propose as proxies for coordinated behaviors.

arXiv:1908.00528

Neural Simplex Architecture

We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of autonomous and other complex systems without unduly sacrificing performance. NSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. In the traditional approach, the advanced controller (AC) is treated as a black box; when the decision module switches control to the baseline controller (BC), the BC remains in control forever. There is relatively little work on switching control back to the AC, and there are no techniques for correcting the AC's behavior after it generates a potentially unsafe control input that causes a failover to the BC. Our NSA addresses both of these limitations. NSA not only provides safety assurances in the presence of a possibly unsafe neural controller, but can also improve the safety of such a controller in an online setting via retraining, without overly degrading its performance. To demonstrate NSA's benefits, we have conducted several significant case studies in the continuous control domain. These include a target-seeking ground rover navigating an obstacle field, and a neural controller for an artificial pancreas system.

arXiv:1907.13122공식 코드 · Papers with Code

Learning Stabilizable Nonlinear Dynamics with Contraction-Based Regularization

We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics. The key contribution is a control-theoretic regularizer for dynamics fitting rooted in the notion of stabilizability, a constraint which guarantees the existence of robust tracking controllers for arbitrary open-loop trajectories generated with the learned system. Leveraging tools from contraction theory and statistical learning in Reproducing Kernel Hilbert Spaces, we formulate stabilizable dynamics learning as a functional optimization with convex objective and bi-convex functional constraints. Under a mild structural assumption and relaxation of the functional constraints to sampling-based constraints, we derive the optimal solution with a modified Representer theorem. Finally, we utilize random matrix feature approximations to reduce the dimensionality of the search parameters and formulate an iterative convex optimization algorithm that jointly fits the dynamics functions and searches for a certificate of stabilizability. We validate the proposed algorithm in simulation for a planar quadrotor, and on a quadrotor hardware testbed emulating planar dynamics. We verify, both in simulation and on hardware, significantly improved trajectory generation and tracking performance with the control-theoretic regularized model over models learned using traditional regression techniques, especially when learning from small supervised datasets. The results support the conjecture that the use of stabilizability constraints as a form of regularization can help prune the hypothesis space in a manner that is tailored to the downstream task of trajectory generation and feedback control, resulting in models that are not only dramatically better conditioned, but also data efficient.

arXiv:1907.05431

Imitation-Projected Programmatic Reinforcement Learning

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.