PyTorchKR Papers

최신 논문

총 991편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2209.12427공식 코드 · Papers with Code

Learning Continuous Control Policies for Information-Theoretic Active Perception

This paper proposes a method for learning continuous control policies for active landmark localization and exploration using an information-theoretic cost. We consider a mobile robot detecting landmarks within a limited sensing range, and tackle the problem of learning a control policy that maximizes the mutual information between the landmark states and the sensor observations. We employ a Kalman filter to convert the partially observable problem in the landmark state to Markov decision process (MDP), a differentiable field of view to shape the reward, and an attention-based neural network to represent the control policy. The approach is further unified with active volumetric mapping to promote exploration in addition to landmark localization. The performance is demonstrated in several simulated landmark localization tasks in comparison with benchmark methods.

arXiv:2209.10072

On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies

Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance. However, the gradient conflict problem is still poorly understood in Meta-RL, which may lead to performance degradation when encountering distinct tasks. To tackle this challenge, this paper proposes a novel personalized Meta-RL (pMeta-RL) algorithm, which aggregates task-specific personalized policies to update a meta-policy used for all tasks, while maintaining personalized policies to maximize the average return of each task under the constraint of the meta-policy. We also provide the theoretical analysis under the tabular setting, which demonstrates the convergence of our pMeta-RL algorithm. Moreover, we extend the proposed pMeta-RL algorithm to a deep network version based on soft actor-critic, making it suitable for continuous control tasks. Experiment results show that the proposed algorithms outperform other previous Meta-RL algorithms on Gym and MuJoCo suites.

arXiv:2209.09441

Locally Constrained Representations in Reinforcement Learning

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can differ vastly across states depending on how the value functions change. However, the representations learned need not be very specific to the task at hand. Relying only on the RL objective may yield representations that vary greatly across successive time steps. In addition, since the RL loss has a changing target, the representations learned would depend on how good the current values/policies are. Thus, disentangling the representations from the main task would allow them to focus not only on the task-specific features but also the environment dynamics. To this end, we propose locally constrained representations, where an auxiliary loss forces the state representations to be predictable by the representations of the neighboring states. This encourages the representations to be driven not only by the value/policy learning but also by an additional loss that constrains the representations from over-fitting to the value loss. We evaluate the proposed method on several known benchmarks and observe strong performance. Especially in continuous control tasks, our experiments show a significant performance improvement.

arXiv:2209.08480

Evolutionary Deep Reinforcement Learning Using Elite Buffer: A Novel Approach Towards DRL Combined with EA in Continuous Control Tasks

Despite the numerous applications and success of deep reinforcement learning in many control tasks, it still suffers from many crucial problems and limitations, including temporal credit assignment with sparse reward, absence of effective exploration, and a brittle convergence that is extremely sensitive to the hyperparameters of the problem. The problems of deep reinforcement learning in continuous control, along with the success of evolutionary algorithms in facing some of these problems, have emerged the idea of evolutionary reinforcement learning, which attracted many controversies. Despite successful results in a few studies in this field, a proper and fitting solution to these problems and their limitations is yet to be presented. The present study aims to study the efficiency of combining the two fields of deep reinforcement learning and evolutionary computations further and take a step towards improving methods and the existing challenges. The "Evolutionary Deep Reinforcement Learning Using Elite Buffer" algorithm introduced a novel mechanism through inspiration from interactive learning capability and hypothetical outcomes in the human brain. In this method, the utilization of the elite buffer (which is inspired by learning based on experience generalization in the human mind), along with the existence of crossover and mutation operators, and interactive learning in successive generations, have improved efficiency, convergence, and proper advancement in the field of continuous control. According to the results of experiments, the proposed method surpasses other well-known methods in environments with high complexity and dimension and is superior in resolving the mentioned problems and limitations.

arXiv:2209.08033

Learning Policies for Continuous Control via Transition Models

It is doubtful that animals have perfect inverse models of their limbs (e.g., what muscle contraction must be applied to every joint to reach a particular location in space). However, in robot control, moving an arm's end-effector to a target position or along a target trajectory requires accurate forward and inverse models. Here we show that by learning the transition (forward) model from interaction, we can use it to drive the learning of an amortized policy. Hence, we revisit policy optimization in relation to the deep active inference framework and describe a modular neural network architecture that simultaneously learns the system dynamics from prediction errors and the stochastic policy that generates suitable continuous control commands to reach a desired reference position. We evaluated the model by comparing it against the baseline of a linear quadratic regulator, and conclude with additional steps to take toward human-like motor control.

arXiv:2209.07364공식 코드 · Papers with Code

Continuous MDP Homomorphisms and Homomorphic Policy Gradient

Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms. In this paper, we study abstraction in the continuous-control setting. We extend the definition of MDP homomorphisms to encompass continuous actions in continuous state spaces. We derive a policy gradient theorem on the abstract MDP, which allows us to leverage approximate symmetries of the environment for policy optimization. Based on this theorem, we propose an actor-critic algorithm that is able to learn the policy and the MDP homomorphism map simultaneously, using the lax bisimulation metric. We demonstrate the effectiveness of our method on benchmark tasks in the DeepMind Control Suite. Our method's ability to utilize MDP homomorphisms for representation learning leads to improved performance when learning from pixel observations.

arXiv:2209.07074공식 코드 · Papers with Code

On the Reuse Bias in Off-Policy Reinforcement Learning

Importance sampling (IS) is a popular technique in off-policy evaluation, which re-weights the return of trajectories in the replay buffer to boost sample efficiency. However, training with IS can be unstable and previous attempts to address this issue mainly focus on analyzing the variance of IS. In this paper, we reveal that the instability is also related to a new notion of Reuse Bias of IS -- the bias in off-policy evaluation caused by the reuse of the replay buffer for evaluation and optimization. We theoretically show that the off-policy evaluation and optimization of the current policy with the data from the replay buffer result in an overestimation of the objective, which may cause an erroneous gradient update and degenerate the performance. We further provide a high-probability upper bound of the Reuse Bias, and show that controlling one term of the upper bound can control the Reuse Bias by introducing the concept of stability for off-policy algorithms. Based on these analyses, we finally present a novel Bias-Regularized Importance Sampling (BIRIS) framework along with practical algorithms, which can alleviate the negative impact of the Reuse Bias. Experimental results show that our BIRIS-based methods can significantly improve the sample efficiency on a series of continuous control tasks in MuJoCo.

arXiv:2209.07288공식 코드 · Papers with Code

Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping

In this work, we study the simple yet universally applicable case of reward shaping in value-based Deep Reinforcement Learning (DRL). We show that reward shifting in the form of the linear transformation is equivalent to changing the initialization of the $Q$-function in function approximation. Based on such an equivalence, we bring the key insight that a positive reward shifting leads to conservative exploitation, while a negative reward shifting leads to curiosity-driven exploration. Accordingly, conservative exploitation improves offline RL value estimation, and optimistic value estimation improves exploration for online RL. We validate our insight on a range of RL tasks and show its improvement over baselines: (1) In offline RL, the conservative exploitation leads to improved performance based on off-the-shelf algorithms; (2) In online continuous control, multiple value functions with different shifting constants can be used to tackle the exploration-exploitation dilemma for better sample efficiency; (3) In discrete control tasks, a negative reward shifting yields an improvement over the curiosity-based exploration method.

arXiv:2209.01947

MO2: Model-Based Offline Options

The ability to discover useful behaviours from past experience and transfer them to new tasks is considered a core component of natural embodied intelligence. Inspired by neuroscience, discovering behaviours that switch at bottleneck states have been long sought after for inducing plans of minimum description length across tasks. Prior approaches have either only supported online, on-policy, bottleneck state discovery, limiting sample-efficiency, or discrete state-action domains, restricting applicability. To address this, we introduce Model-Based Offline Options (MO2), an offline hindsight framework supporting sample-efficient bottleneck option discovery over continuous state-action spaces. Once bottleneck options are learnt offline over source domains, they are transferred online to improve exploration and value estimation on the transfer domain. Our experiments show that on complex long-horizon continuous control tasks with sparse, delayed rewards, MO2's properties are essential and lead to performance exceeding recent option learning methods. Additional ablations further demonstrate the impact on option predictability and credit assignment.

arXiv:2209.00532공식 코드 · Papers with Code

Actor Prioritized Experience Replay

A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error. Although it has been shown that PER is one of the most crucial components for the overall performance of deep RL methods in discrete action domains, many empirical studies indicate that it considerably underperforms actor-critic algorithms in continuous control. We theoretically show that actor networks cannot be effectively trained with transitions that have large TD errors. As a result, the approximate policy gradient computed under the Q-network diverges from the actual gradient computed under the optimal Q-function. Motivated by this, we introduce a novel experience replay sampling framework for actor-critic methods, which also regards issues with stability and recent findings behind the poor empirical performance of PER. The introduced algorithm suggests a new branch of improvements to PER and schedules effective and efficient training for both actor and critic networks. An extensive set of experiments verifies our theoretical claims and demonstrates that the introduced method significantly outperforms the competing approaches and obtains state-of-the-art results over the standard off-policy actor-critic algorithms.

arXiv:2208.13125

Normality-Guided Distributional Reinforcement Learning for Continuous Control

Learning a predictive model of the mean return, or value function, plays a critical role in many reinforcement learning algorithms. Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value distribution, not just the mean. We study the value distribution in several continuous control tasks and find that the learned value distribution is empirical quite close to normal. We design a method that exploits this property, employ variances predicted from a variance network, along with returns, to analytically compute target quantile bars representing a normal for our distributional value function. In addition, we propose a policy update strategy based on the correctness as measured by structural characteristics of the value distribution not present in the standard value function. The approach we outline is compatible with many DRL structures. We use two representative on-policy algorithms, PPO and TRPO, as testbeds. Our method yields statistically significant improvements in 10 out of 16 continuous task settings, while utilizing a reduced number of weights and achieving faster training time compared to an ensemble-based method for quantifying value distribution uncertainty.

arXiv:2208.11140

Improvement of Sliding Mode Control Strategy Founded on Cascaded Doubly Fed Induction Generator Powered by a Matrix Converter

The current paper presents a Sliding Mode Controller (SMC) for indirect field-oriented Cascaded Doubly Fed Induction Generator (CDFIG) powered through a Matrix Converter (MC). The proposed SMC employs a continuous control strategy to accomplish free chattering fractional-order sliding-mode control and to ensure that the control of the first DFIG stator's reactive and active power is separated. An MC is used to control the current provided to the second stator of the CDFIG as an alternative to standard voltage source inverters. The two MCs are controlled via Space-Vector Pulse-Width Modulation (SVPWM) and Indirect Field Oriented Control (IFOC). The proposed Wind Power Generation System (WPGS) is used with the purpose to ensure Maximum Power Point Tracking (MPPT) sensing under various disturbance variables such as turbulent wind. The simulation results prove the efficiency and robustness of the proposed method.

arXiv:2208.10291공식 코드 · Papers with Code

Efficient Planning in a Compact Latent Action Space

Planning-based reinforcement learning has shown strong performance in tasks in discrete and low-dimensional continuous action spaces. However, planning usually brings significant computational overhead for decision-making, and scaling such methods to high-dimensional action spaces remains challenging. To advance efficient planning for high-dimensional continuous control, we propose Trajectory Autoencoding Planner (TAP), which learns low-dimensional latent action codes with a state-conditional VQ-VAE. The decoder of the VQ-VAE thus serves as a novel dynamics model that takes latent actions and current state as input and reconstructs long-horizon trajectories. During inference time, given a starting state, TAP searches over discrete latent actions to find trajectories that have both high probability under the training distribution and high predicted cumulative reward. Empirical evaluation in the offline RL setting demonstrates low decision latency which is indifferent to the growing raw action dimensionality. For Adroit robotic hand manipulation tasks with high-dimensional continuous action space, TAP surpasses existing model-based methods by a large margin and also beats strong model-free actor-critic baselines.

arXiv:2208.07914공식 코드 · Papers with Code

PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm

Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given domain with a single training is critical. To this end, we propose a novel MORL algorithm that trains a single universal network to cover the entire preference space scalable to continuous robotic tasks. The proposed approach, Preference-Driven MORL (PD-MORL), utilizes the preferences as guidance to update the network parameters. It also employs a novel parallelization approach to increase sample efficiency. We show that PD-MORL achieves up to 25% larger hypervolume for challenging continuous control tasks and uses an order of magnitude fewer trainable parameters compared to prior approaches.

arXiv:2208.07156

Cooperative guidance of multiple missiles: a hybrid co-evolutionary approach

Cooperative guidance of multiple missiles is a challenging task with rigorous constraints of time and space consensus, especially when attacking dynamic targets. In this paper, the cooperative guidance task is described as a distributed multi-objective cooperative optimization problem. To address the issues of non-stationarity and continuous control faced by cooperative guidance, the natural evolutionary strategy (NES) is improved along with an elitist adaptive learning technique to develop a novel natural co-evolutionary strategy (NCES). The gradients of original evolutionary strategy are rescaled to reduce the estimation bias caused by the interaction between the multiple missiles. Then, a hybrid co-evolutionary cooperative guidance law (HCCGL) is proposed by integrating the highly scalable co-evolutionary mechanism and the traditional guidance strategy. Finally, three simulations under different conditions demonstrate the effectiveness and superiority of this guidance law in solving cooperative guidance tasks with high accuracy. The proposed co-evolutionary approach has great prospects not only in cooperative guidance, but also in other application scenarios of multi-objective optimization, dynamic optimization and distributed control.

arXiv:2208.06169

DDX7: Differentiable FM Synthesis of Musical Instrument Sounds

FM Synthesis is a well-known algorithm used to generate complex timbre from a compact set of design primitives. Typically featuring a MIDI interface, it is usually impractical to control it from an audio source. On the other hand, Differentiable Digital Signal Processing (DDSP) has enabled nuanced audio rendering by Deep Neural Networks (DNNs) that learn to control differentiable synthesis layers from arbitrary sound inputs. The training process involves a corpus of audio for supervision, and spectral reconstruction loss functions. Such functions, while being great to match spectral amplitudes, present a lack of pitch direction which can hinder the joint optimization of the parameters of FM synthesizers. In this paper, we take steps towards enabling continuous control of a well-established FM synthesis architecture from an audio input. Firstly, we discuss a set of design constraints that ease spectral optimization of a differentiable FM synthesizer via a standard reconstruction loss. Next, we present Differentiable DX7 (DDX7), a lightweight architecture for neural FM resynthesis of musical instrument sounds in terms of a compact set of parameters. We train the model on instrument samples extracted from the URMP dataset, and quantitatively demonstrate its comparable audio quality against selected benchmarks.

arXiv:2208.06033공식 코드 · Papers with Code

Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning

Adopting reasonable strategies is challenging but crucial for an intelligent agent with limited resources working in hazardous, unstructured, and dynamic environments to improve the system's utility, decrease the overall cost, and increase mission success probability. This paper proposes a novel directed acyclic strategy graph decomposition approach based on Bayesian chaining to separate an intricate policy into several simple sub-policies and organize their relationships as Bayesian strategy networks (BSN). We integrate this approach into the state-of-the-art DRL method -- soft actor-critic (SAC), and build the corresponding Bayesian soft actor-critic (BSAC) model by organizing several sub-policies as a joint policy. We compare our method against the state-of-the-art deep reinforcement learning algorithms on the standard continuous control benchmarks in the OpenAI Gym environment. The results demonstrate that the promising potential of the BSAC method significantly improves training efficiency.

arXiv:2208.02225공식 코드 · Papers with Code

Sequence Model Imitation Learning with Unobserved Contexts

We consider imitation learning problems where the learner's ability to mimic the expert increases throughout the course of an episode as more information is revealed. One example of this is when the expert has access to privileged information: while the learner might not be able to accurately reproduce expert behavior early on in an episode, by considering the entire history of states and actions, they might be able to eventually identify the hidden context and act as the expert would. We prove that on-policy imitation learning algorithms (with or without access to a queryable expert) are better equipped to handle these sorts of asymptotically realizable problems than off-policy methods. This is because on-policy algorithms provably learn to recover from their initially suboptimal actions, while off-policy methods treat their suboptimal past actions as though they came from the expert. This often manifests as a latching behavior: a naive repetition of past actions. We conduct experiments in a toy bandit domain that show that there exist sharp phase transitions of whether off-policy approaches are able to match expert performance asymptotically, in contrast to the uniformly good performance of on-policy approaches. We demonstrate that on several continuous control tasks, on-policy approaches are able to use history to identify the context while off-policy approaches actually perform worse when given access to history.

arXiv:2208.00755공식 코드 · Papers with Code

Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy between the underlying distributions of the agent's policy and collected data increases. Although the well-studied importance sampling and off-policy policy gradient techniques were proposed to compensate for this discrepancy, they usually require a collection of long trajectories and induce additional problems such as vanishing/exploding gradients or discarding many useful experiences, which eventually increases the computational complexity. Moreover, their generalization to either continuous action domains or policies approximated by deterministic deep neural networks is strictly limited. To overcome these limitations, we introduce a novel policy similarity measure to mitigate the effects of such discrepancy in continuous control. Our method offers an adequate single-step off-policy correction that is applicable to deterministic policy networks. Theoretical and empirical studies demonstrate that it can achieve a "safe" off-policy learning and substantially improve the state-of-the-art by attaining higher returns in fewer steps than the competing methods through an effective schedule of the learning rate in Q-learning and policy optimization.

arXiv:2207.14723

Meta Reinforcement Learning with Successor Feature Based Context

Most reinforcement learning (RL) methods only focus on learning a single task from scratch and are not able to use prior knowledge to learn other tasks more effectively. Context-based meta RL techniques are recently proposed as a possible solution to tackle this. However, they are usually less efficient than conventional RL and may require many trial-and-errors during training. To address this, we propose a novel meta-RL approach that achieves competitive performance comparing to existing meta-RL algorithms, while requires significantly fewer environmental interactions. By combining context variables with the idea of decomposing reward in successor feature framework, our method does not only learn high-quality policies for multiple tasks simultaneously but also can quickly adapt to new tasks with a small amount of training. Compared with state-of-the-art meta-RL baselines, we empirically show the effectiveness and data efficiency of our method on several continuous control tasks.