اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدAdaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
107
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two methods are known to achieve complementary bias-variance trade-off properties, with TD tending to achieve lower variance but potentially higher bias. In this paper, we argue that the larger bias of TD can be a result of the amplification of local approximation errors. We address this by proposing an algorithm that adaptively switches between TD and MC in each state, thus mitigating the propagation of errors. Our method is based on learned confidence intervals that detect biases of TD estimates. We demonstrate in a variety of policy evaluation tasks that this simple adaptive algorithm performs competitively with the best approach in hindsight, suggesting that learned confidence intervals are a powerful technique for adapting policy evaluation to use TD or MC returns in a data-driven way.
قيم البحث
اقرأ أيضاً
Temporal Difference learning or TD($lambda$) is a fundamental algorithm in the field of reinforcement learning. However, setting TDs $lambda$ parameter, which controls the timescale of TD updates, is generally left up to the practitioner. We formaliz
e the $lambda$ selection problem as a bias-variance trade-off where the solution is the value of $lambda$ that leads to the smallest Mean Squared Value Error (MSVE). To solve this trade-off we suggest applying Leave-One-Trajectory-Out Cross-Validation (LOTO-CV) to search the space of $lambda$ values. Unfortunately, this approach is too computationally expensive for most practical applications. For Least Squares TD (LSTD) we show that LOTO-CV can be implemented efficiently to automatically tune $lambda$ and apply function optimization methods to efficiently search the space of $lambda$ values. The resulting algorithm, ALLSTD, is parameter free and our experiments demonstrate that ALLSTD is significantly computationally faster than the na{i}ve LOTO-CV implementation while achieving similar performance.
The evaluation of rare but high-stakes events remains one of the main difficulties in obtaining reliable policies from intelligent agents, especially in large or continuous state/action spaces where limited scalability enforces the use of a prohibiti
vely large number of testing iterations. On the other hand, a biased or inaccurate policy evaluation in a safety-critical system could potentially cause unexpected catastrophic failures during deployment. In this paper, we propose the Accelerated Policy Evaluation (APE) method, which simultaneously uncovers rare events and estimates the rare event probability in Markov decision processes. The APE method treats the environment nature as an adversarial agent and learns towards, through adaptive importance sampling, the zero-variance sampling distribution for the policy evaluation. Moreover, APE is scalable to large discrete or continuous spaces by incorporating function approximators. We investigate the convergence properties of proposed algorithms under suitable regularity conditions. Our empirical studies show that APE estimates rare event probability with a smaller variance while only using orders of magnitude fewer samples compared to baseline methods in both multi-agent and single-agent environments.
It is still common to use Q-learning and temporal difference (TD) learning-even though they have divergence issues and sound Gradient TD alternatives exist-because divergence seems rare and they typically perform well. However, recent work with large
neural network learning systems reveals that instability is more common than previously thought. Practitioners face a difficult dilemma: choose an easy to use and performant TD method, or a more complex algorithm that is more sound but harder to tune and all but unexplored with non-linear function approximation or control. In this paper, we introduce a new method called TD with Regularized Corrections (TDRC), that attempts to balance ease of use, soundness, and performance. It behaves as well as TD, when TD performs well, but is sound in cases where TD diverges. We empirically investigate TDRC across a range of problems, for both prediction and control, and for both linear and non-linear function approximation, and show, potentially for the first time, that gradient TD methods could be a better alternative to TD and Q-learning.
Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because of the ex
pensiveness of interaction and limitation of budget at deployment. One aspect of the data inefficiency comes from the expensive hyper-parameter tuning when optimizing deep neural networks. We propose Adaptive Behavior Policy Sharing (ABPS), a data-efficient training algorithm that allows sharing of experience collected by behavior policy that is adaptively selected from a pool of agents trained with an ensemble of hyper-parameters. We further extend ABPS to evolve hyper-parameters during training by hybridizing ABPS with an adapted version of Population Based Training (ABPS-PBT). We conduct experiments with multiple Atari games with up to 16 hyper-parameter/architecture setups. ABPS achieves superior overall performance, reduced variance on top 25% agents, and equivalent performance on the best agent compared to conventional hyper-parameter tuning with independent training, even though ABPS only requires the same number of environmental interactions as training a single agent. We also show that ABPS-PBT further improves the convergence speed and reduces the variance.
Learning a policy using only observational data is challenging because the distribution of states it induces at execution time may differ from the distribution observed during training. We propose to train a policy by unrolling a learned model of the
environment dynamics over multiple time steps while explicitly penalizing two costs: the original cost the policy seeks to optimize, and an uncertainty cost which represents its divergence from the states it is trained on. We measure this second cost by using the uncertainty of the dynamics model about its own predictions, using recent ideas from uncertainty estimation for deep networks. We evaluate our approach using a large-scale observational dataset of driving behavior recorded from traffic cameras, and show that we are able to learn effective driving policies from purely observational data, with no environment interaction.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
