Amortized Variational Deep Q Network

• URL: http://arxiv.org/abs/2011.01706v1
• Date: Tue, 3 Nov 2020 13:48:18 GMT
• Title: Amortized Variational Deep Q Network
• Authors: Haotian Zhang, Yuhao Wang, Jianyong Sun, Zongben Xu
• Abstract summary: We propose an amortized variational inference framework to approximate the posterior distribution of the action value function in Deep Q Network. We show that the amortized framework can results in significant less learning parameters than existing state-of-the-art method.
• Score: 28.12600565839504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Efficient exploration is one of the most important issues in deep reinforcement learning. To address this issue, recent methods consider the value function parameters as random variables, and resort variational inference to approximate the posterior of the parameters. In this paper, we propose an amortized variational inference framework to approximate the posterior distribution of the action value function in Deep Q Network. We establish the equivalence between the loss of the new model and the amortized variational inference loss. We realize the balance of exploration and exploitation by assuming the posterior as Cauchy and Gaussian, respectively in a two-stage training process. We show that the amortized framework can results in significant less learning parameters than existing state-of-the-art method. Experimental results on classical control tasks in OpenAI Gym and chain Markov Decision Process tasks show that the proposed method performs significantly better than state-of-art methods and requires much less training time.

Related papers

• Sublinear Regret for a Class of Continuous-Time Linear--Quadratic Reinforcement Learning Problems [10.404992912881601]
  We study reinforcement learning for a class of continuous-time linear-quadratic (LQ) control problems for diffusions. We apply a model-free approach that relies neither on knowledge of model parameters nor on their estimations, and devise an actor-critic algorithm to learn the optimal policy parameter directly.
  arXiv  Detail & Related papers  (2024-07-24T12:26:21Z)
• Fast Value Tracking for Deep Reinforcement Learning [7.648784748888187]
  Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interact with their environment. Existing algorithms often view these problem as static, focusing on point estimates for model parameters to maximize expected rewards. Our research leverages the Kalman paradigm to introduce a novel quantification and sampling algorithm called Langevinized Kalman TemporalTD.
  arXiv  Detail & Related papers  (2024-03-19T22:18:19Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Adaptive Robust Learning using Latent Bernoulli Variables [50.223140145910904]
  We present an adaptive approach for learning from corrupted training sets. We identify corrupted non-corrupted samples with latent Bernoulli variables. The resulting problem is solved via variational inference.
  arXiv  Detail & Related papers  (2023-12-01T13:50:15Z)
• Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning [19.850893012601638]
  Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. We propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning.
  arXiv  Detail & Related papers  (2023-11-26T01:44:01Z)
• Value-Distributional Model-Based Reinforcement Learning [59.758009422067]
  Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective. We propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function.
  arXiv  Detail & Related papers  (2023-08-12T14:59:19Z)
• Model-Based Uncertainty in Value Functions [89.31922008981735]
  We focus on characterizing the variance over values induced by a distribution over MDPs. Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation. We propose a new uncertainty Bellman equation whose solution converges to the true posterior variance over values.
  arXiv  Detail & Related papers  (2023-02-24T09:18:27Z)
• Variational Laplace Autoencoders [53.08170674326728]
  Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. We present a novel approach that addresses the limited posterior expressiveness of fully-factorized Gaussian assumption. We also present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models.
  arXiv  Detail & Related papers  (2022-11-30T18:59:27Z)
• Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime [9.184987303791292]
  We show that in permuted MNIST image classification tasks, the performance of multilayer perceptrons trained by vanilla gradient descent can be improved. We provide a theoretical explanation of this effect by studying a qualitatively similar two-task linear regression problem. We show that when a model is trained on the two tasks in sequence without any additional regularization, the risk gain on the first task is small.
  arXiv  Detail & Related papers  (2022-06-01T18:04:33Z)
• Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning [99.34907092347733]
  We analyze the problem of estimating optimal $Q$-value functions for a discounted Markov decision process with discrete states and actions. Using a local minimax framework, we show that this functional arises in lower bounds on the accuracy on any estimation procedure. In the other direction, we establish the sharpness of our lower bounds, up to factors logarithmic in the state and action spaces, by analyzing a variance-reduced version of $Q$-learning.
  arXiv  Detail & Related papers  (2021-06-28T00:38:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.