اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDeep Exploration via Randomized Value Functions
107
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to value function learning. We present several reinforcement learning algorithms that leverage randomized value functions and demonstrate their efficacy through computational studies. We also prove a regret bound that establishes statistical efficiency with a tabular representation.
قيم البحث
اقرأ أيضاً
Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decisio
n problems. Other methods, such as bootstrap sampling, have no mechanism for uncertainty that does not come from the observed data. We highlight why this can be a crucial shortcoming and propose a simple remedy through addition of a randomized untrainable `prior network to each ensemble member. We prove that this approach is efficient with linear representations, provide simple illustrations of its efficacy with nonlinear representations and show that this approach scales to large-scale problems far better than previous attempts.
We discuss the relative merits of optimistic and randomized approaches to exploration in reinforcement learning. Optimistic approaches presented in the literature apply an optimistic boost to the value estimate at each state-action pair and select ac
tions that are greedy with respect to the resulting optimistic value function. Randomized approaches sample from among statistically plausible value functions and select actions that are greedy with respect to the random sample. Prior computational experience suggests that randomized approaches can lead to far more statistically efficient learning. We present two simple analytic examples that elucidate why this is the case. In principle, there should be optimistic approaches that fare well relative to randomized approaches, but that would require intractable computation. Optimistic approaches that have been proposed in the literature sacrifice statistical efficiency for the sake of computational efficiency. Randomized approaches, on the other hand, may enable simultaneous statistical and computational efficiency.
Standard RL algorithms assume fixed environment dynamics and require a significant amount of interaction to adapt to new environments. We introduce Policy-Dynamics Value Functions (PD-VF), a novel approach for rapidly adapting to dynamics different f
rom those previously seen in training. PD-VF explicitly estimates the cumulative reward in a space of policies and environments. An ensemble of conventional RL policies is used to gather experience on training environments, from which embeddings of both policies and environments can be learned. Then, a value function conditioned on both embeddings is trained. At test time, a few actions are sufficient to infer the environment embedding, enabling a policy to be selected by maximizing the learned value function (which requires no additional environment interaction). We show that our method can rapidly adapt to new dynamics on a set of MuJoCo domains. Code available at https://github.com/rraileanu/policy-dynamics-value-functions.
Deep neural networks (DNNs) generalize remarkably well without explicit regularization even in the strongly over-parametrized regime where classical learning theory would instead predict that they would severely overfit. While many proposals for some
kind of implicit regularization have been made to rationalise this success, there is no consensus for the fundamental reason why DNNs do not strongly overfit. In this paper, we provide a new explanation. By applying a very general probability-complexity bound recently derived from algorithmic information theory (AIT), we argue that the parameter-function map of many DNNs should be exponentially biased towards simple functions. We then provide clear evidence for this strong simplicity bias in a model DNN for Boolean functions, as well as in much larger fully connected and convolutional networks applied to CIFAR10 and MNIST. As the target functions in many real problems are expected to be highly structured, this intrinsic simplicity bias helps explain why deep networks generalize well on real world problems. This picture also facilitates a novel PAC-Bayes approach where the prior is taken over the DNN input-output function space, rather than the more conventional prior over parameter space. If we assume that the training algorithm samples parameters close to uniformly within the zero-error region then the PAC-Bayes theorem can be used to guarantee good expected generalization for target functions producing high-likelihood training sets. By exploiting recently discovered connections between DNNs and Gaussian processes to estimate the marginal likelihood, we produce relatively tight generalization PAC-Bayes error bounds which correlate well with the true error on realistic datasets such as MNIST and CIFAR10 and for architectures including convolutional and fully connected networks.
We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlike existing upper-confidence-bound (UCB) based approaches, which are of
ten computationally intractable, our algorithm drives exploration by simply perturbing the training data with judiciously chosen i.i.d. scalar noises. To attain optimistic value function estimation without resorting to a UCB-style bonus, we introduce an optimistic reward sampling procedure. When the value functions can be represented by a function class $mathcal{F}$, our algorithm achieves a worst-case regret bound of $widetilde{O}(mathrm{poly}(d_EH)sqrt{T})$ where $T$ is the time elapsed, $H$ is the planning horizon and $d_E$ is the $textit{eluder dimension}$ of $mathcal{F}$. In the linear setting, our algorithm reduces to LSVI-PHE, a variant of RLSVI, that enjoys an $widetilde{mathcal{O}}(sqrt{d^3H^3T})$ regret. We complement the theory with an empirical evaluation across known difficult exploration tasks.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
