Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSuccessive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning
91
0
0.0
(
0
)
Added by
Chang Tian
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We propose a successive convex approximation based off-policy optimization (SCAOPO) algorithm to solve the general constrained reinforcement learning problem, which is formulated as a constrained Markov decision process (CMDP) in the context of average cost. The SCAOPO is based on solving a sequence of convex objective/feasibility optimization problems obtained by replacing the objective and constraint functions in the original problems with convex surrogate functions. At each iteration, the convex surrogate problem can be efficiently solved by Lagrange dual method even the policy is parameterized by a high-dimensional function. Moreover, the SCAOPO enables to reuse old experiences from previous updates, thereby significantly reducing the implementation cost when deployed in the real-world engineering systems that need to online learn the environment. In spite of the time-varying state distribution and the stochastic bias incurred by the off-policy learning, the SCAOPO with a feasible initial point can still provably converge to a Karush-Kuhn-Tucker (KKT) point of the original problem almost surely.
rate research
Read More
Although well-established in general reinforcement learning (RL), value-based methods are rarely explored in constrained RL (CRL) for their incapability of finding policies that can randomize among multiple actions. To apply value-based methods to CRL, a recent groundbreaking line of game-theoretic approaches uses the mixed policy that randomizes among a set of carefully generated policies to converge to the desired constraint-satisfying policy. However, these approaches require storing a large set of policies, which is not policy efficient, and may incur prohibitive memory costs in constrained deep RL. To address this problem, we propose an alternative approach. Our approach first reformulates the CRL to an equivalent distance optimization problem. With a specially designed linear optimization oracle, we derive a meta-algorithm that solves it using any off-the-shelf RL algorithm and any conditional gradient (CG) type algorithm as subroutines. We then propose a new variant of the CG-type algorithm, which generalizes the minimum norm point (MNP) method. The proposed method matches the convergence rate of the existing game-theoretic approaches and achieves the worst-case optimal policy efficiency. The experiments on a navigation task show that our method reduces the memory costs by an order of magnitude, and meanwhile achieves better performance, demonstrating both its effectiveness and efficiency.
Reinforcement learning with function approximation can be unstable and even divergent, especially when combined with off-policy learning and Bellman updates. In deep reinforcement learning, these issues have been dealt with empirically by adapting and regularizing the representation, in particular with auxiliary tasks. This suggests that representation learning may provide a means to guarantee stability. In this paper, we formally show that there are indeed nontrivial state representations under which the canonical TD algorithm is stable, even when learning off-policy. We analyze representation learning schemes that are based on the transition matrix of a policy, such as proto-value functions, along three axes: approximation error, stability, and ease of estimation. In the most general case, we show that a Schur basis provides convergence guarantees, but is difficult to estimate from samples. For a fixed reward function, we find that an orthogonal basis of the corresponding Krylov subspace is an even better choice. We conclude by empirically demonstrating that these stable representations can be learned using stochastic gradient descent, opening the door to improved techniques for representation learning with deep networks.
We propose a policy improvement algorithm for Reinforcement Learning (RL) which is called Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when learning the $Q$-value from finite past experience data. Greedy policies or even constrained policy optimization algorithms which ignore these errors may suffer from an improvement penalty (i.e. a negative policy improvement). To minimize the improvement penalty, the RBI idea is to attenuate rapid policy changes of low probability actions which were less frequently sampled. This approach is shown to avoid catastrophic performance degradation and reduce regret when learning from a batch of past experience. Through a two-armed bandit with Gaussian distributed rewards example, we show that it also increases data efficiency when the optimal action has a high variance. We evaluate RBI in two tasks in the Atari Learning Environment: (1) learning from observations of multiple behavior policies and (2) iterative RL. Our results demonstrate the advantage of RBI over greedy policies and other constrained policy optimization algorithms as a safe learning approach and as a general data efficient learning algorithm. An anonymous Github repository of our RBI implementation is found at https://github.com/eladsar/rbi.
We study deep reinforcement learning (RL) algorithms with delayed rewards. In many real-world tasks, instant rewards are often not readily accessible or even defined immediately after the agent performs actions. In this work, we first formally define the environment with delayed rewards and discuss the challenges raised due to the non-Markovian nature of such environments. Then, we introduce a general off-policy RL framework with a new Q-function formulation that can handle the delayed rewards with theoretical convergence guarantees. For practical tasks with high dimensional state spaces, we further introduce the HC-decomposition rule of the Q-function in our framework which naturally leads to an approximation scheme that helps boost the training efficiency and stability. We finally conduct extensive experiments to demonstrate the superior performance of our algorithms over the existing work and their variants.
This paper introduces a machine learning based collaborative multi-band spectrum sensing policy for cognitive radios. The proposed sensing policy guides secondary users to focus the search of unused radio spectrum to those frequencies that persistently provide them high data rate. The proposed policy is based on machine learning, which makes it adaptive with the temporally and spatially varying radio spectrum. Furthermore, there is no need for dynamic modeling of the primary activity since it is implicitly learned over time. Energy efficiency is achieved by minimizing the number of assigned sensors per each subband under a constraint on miss detection probability. It is important to control the missed detections because they cause collisions with primary transmissions and lead to retransmissions at both the primary and secondary user. Simulations show that the proposed machine learning based sensing policy improves the overall throughput of the secondary network and improves the energy efficiency while controlling the miss detection probability.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
