An official website of the United States government
This paper provides a finite-sample analysis of a passive stochastic gradient Langevin dynamics (PSGLD) algo- rithm. This algorithm is designed to achieve adaptive inverse reinforcement learning (IRL). Adaptive IRL aims to estimate the cost function of a forward learner performing a stochastic gradient algorithm (e.g., policy gradient reinforcement learning) by observing their estimates in real-time. The PSGLD algorithm is considered passive because it incorporates noisy gradients provided by an external stochastic gradient algorithm (forward learner), of which it has no control. The PSGLD algorithm acts as a randomized sampler to achieve adaptive IRL by reconstructing the forward learner’s cost function nonparametrically from the stationary measure of a Langevin diffusion. This paper analyzes the non-asymptotic (finite-sample) performance; we provide explicit bounds on the 2-Wasserstein distance between PSGLD algorithm sample measure and the stationary measure encoding the cost function, and provide guarantees for a kernel density estimation scheme which reconstructs the cost function from empirical samples. Our analysis uses tools from the study of Markov diffusion operators. The derived bounds have both practical and theoretical significance. They provide finite-time guarantees for an adaptive IRL mechanism, and substantially generalize the analytical framework of a line of research in passive stochastic gradient algorithms.
more »
« less
Policy Gradient using Weak Derivatives for Reinforcement Learning
This paper considers policy search in continuous state-action reinforcement learning problems. Typically, one computes search directions using a classic expression for the policy gradient called the Policy Gradient Theorem, which decomposes the gradient of the value function into two factors: the score function and the Q-function. This paper presents four results: (i) an alternative policy gradient theorem using weak (measure-valued) derivatives instead of score-function is established; (ii) the stochastic gradient estimates thus derived are shown to be unbiased and to yield algorithms that converge almost surely to stationary points of the non-convex value function of the reinforcement learning problem; (iii) the sample complexity of the algorithm is derived and is shown to be O(1/ k); (iv) finally, the expected variance of the gradient estimates obtained using weak derivatives is shown to be lower than those obtained using the popular score-function approach. Experiments on OpenAI gym pendulum environment illustrate the superior performance of the proposed algorithm.
more »
« less
- Award ID(s):
- 1714180
- PAR ID:
- 10161725
- Date Published:
- Journal Name:
- 2019 IEEE 58th Conference on Decision and Control
- Page Range / eLocation ID:
- 5531 to 5537
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interacts with their environment. However, existing algorithms often view these problem as static, focusing on point estimates for model parameters to maximize expected rewards, neglecting the stochastic dynamics of agent-environment interactions and the critical role of uncertainty quantification. Our research leverages the Kalman filtering paradigm to introduce a novel and scalable sampling algorithm called Langevinized Kalman Temporal-Difference (LKTD) for deep reinforcement learning. This algorithm, grounded in Stochastic Gradient Markov Chain Monte Carlo (SGMCMC), efficiently draws samples from the posterior distribution of deep neural network parameters. Under mild conditions, we prove that the posterior samples generated by the LKTD algorithm converge to a stationary distribution. This convergence not only enables us to quantify uncertainties associated with the value function and model parameters but also allows us to monitor these uncertainties during policy updates throughout the training phase. The LKTD algorithm paves the way for more robust and adaptable reinforcement learning approaches.more » « less
-
Astolfi, Alessandro (Ed.)Q-learning has become an important part of the reinforcement learning toolkit since its introduction in the dissertation of Chris Watkins in the 1980s. In the original tabular formulation, the goal is to compute exactly a solution to the discounted-cost optimality equation, and thereby obtain the optimal policy for a Markov Decision Process. The goal today is more modest: obtain an approximate solution within a prescribed function class. The standard algorithms are based on the same architecture as formulated in the 1980s, with the goal of finding a value function approximation that solves the so-called projected Bellman equation. While reinforcement learning has been an active research area for over four decades, there is little theory providing conditions for convergence of these Q-learning algorithms, or even existence of a solution to this equation. The purpose of this paper is to show that a solution to the projected Bellman equation does exist, provided the function class is linear and the input used for training is a form of epsilon-greedy policy with sufficiently small epsilon. Moreover, under these conditions it is shown that the Q-learning algorithm is stable, in terms of bounded parameter estimates. Convergence remains one of many open topics for research.more » « less
-
Melo, S. F.; Fang. F. (Ed.)Existing risk-averse reinforcement learning approaches still face several challenges, including the lack of global optimality guarantee and the necessity of learning from long-term consecutive trajectories. Long-term consecutive trajectories are prone to involving visiting hazardous states, which is a major concern in the risk-averse setting. This paper proposes Transition-based vOlatility-controlled Policy Search (TOPS), a novel algorithm that solves risk-averse problems by learning from transitions. We prove that our algorithm—under the over-parameterized neural network regime—finds a globally optimal policy at a sublinear rate with proximal policy optimization and natural policy gradient. The convergence rate is comparable to the state-of-the-art risk-neutral policy-search methods. The algorithm is evaluated on challenging Mujoco robot simulation tasks under the mean-variance evaluation metric. Both theoretical analysis and experimental results demonstrate a state-of-the-art level of TOPS’ performance among existing risk-averse policy search methods.more » « less
-
In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobserved factors, inducing confounding and biasing estimates derived assuming a perfect Markov decision process (MDP) model. In “Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes,” A. Bennett and N. Kallus tackle this by considering off-policy evaluation in a partially observed MDP (POMDP). Specifically, they consider estimating the value of a given target policy in an unknown POMDP, given observations of trajectories generated by a different and unknown policy, which may depend on the unobserved states. They consider both when the target policy value can be identified the observed data and, given identification, how best to estimate it. Both these problems are addressed by extending the framework of proximal causal inference to POMDP settings, using sequences of so-called bridge functions. This results in a novel framework for off-policy evaluation in POMDPs that they term proximal reinforcement learning, which they validate in various empirical settings.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/CDC40024.2019.9029403
