PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

• URL: http://arxiv.org/abs/2007.08459v2
• Date: Thu, 13 Aug 2020 17:59:40 GMT
• Title: PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
• Authors: Alekh Agarwal, Mikael Henaff, Sham Kakade, Wen Sun
• Abstract summary: This work introduces the the Policy Cover-Policy Gradient (PC-PG) algorithm, which balances the exploration vs. exploitation tradeoff using an ensemble of policies (the policy cover) We show that PC-PG has strong guarantees under model misspecification that go beyond the standard worst case $ell_infty$ assumptions. We also complement the theory with empirical evaluation across a variety of domains in both reward-free and reward-driven settings.
• Score: 35.044047991893365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct policy gradient methods for reinforcement learning are a successful approach for a variety of reasons: they are model free, they directly optimize the performance metric of interest, and they allow for richly parameterized policies. Their primary drawback is that, by being local in nature, they fail to adequately explore the environment. In contrast, while model-based approaches and Q-learning directly handle exploration through the use of optimism, their ability to handle model misspecification and function approximation is far less evident. This work introduces the the Policy Cover-Policy Gradient (PC-PG) algorithm, which provably balances the exploration vs. exploitation tradeoff using an ensemble of learned policies (the policy cover). PC-PG enjoys polynomial sample complexity and run time for both tabular MDPs and, more generally, linear MDPs in an infinite dimensional RKHS. Furthermore, PC-PG also has strong guarantees under model misspecification that go beyond the standard worst case $\ell_{\infty}$ assumptions; this includes approximation guarantees for state aggregation under an average case error assumption, along with guarantees under a more general assumption where the approximation error under distribution shift is controlled. We complement the theory with empirical evaluation across a variety of domains in both reward-free and reward-driven settings.

Related papers

• Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning [62.81324245896717]
  We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-ite convergence guarantees under (weak) gradient domination assumptions. We numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-07-15T14:54:57Z)
• Policy Gradient with Active Importance Sampling [55.112959067035916]
  Policy gradient (PG) methods significantly benefit from IS, enabling the effective reuse of previously collected samples. However, IS is employed in RL as a passive tool for re-weighting historical samples. We look for the best behavioral policy from which to collect samples to reduce the policy gradient variance.
  arXiv  Detail & Related papers  (2024-05-09T09:08:09Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Score-Aware Policy-Gradient Methods and Performance Guarantees using Local Lyapunov Conditions: Applications to Product-Form Stochastic Networks and Queueing Systems [1.747623282473278]
  We introduce a policygradient method for model reinforcement learning (RL) that exploits a type of stationary distributions commonly obtained from decision processes (MDPs) in networks. Specifically, when the stationary distribution of the MDP is parametrized by policy parameters, we can improve existing policy methods for average-reward estimation.
  arXiv  Detail & Related papers  (2023-12-05T14:44:58Z)
• Stochastic first-order methods for average-reward Markov decision processes [10.023632561462712]
  We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluation. By combining the policy evaluation and policy optimization parts, we establish sample complexity results for solving AMDPs under both generative and Markovian noise models.
  arXiv  Detail & Related papers  (2022-05-11T23:02:46Z)
• Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration [39.250754806600135]
  Policy (PG) estimation becomes a challenge when we are not allowed to sample with the target policy. Conventional methods for off-policy PG estimation often suffer from significant bias or exponentially large variance. In this paper, we propose the double Fitted PG estimation (FPG) algorithm.
  arXiv  Detail & Related papers  (2022-01-31T20:23:52Z)
• A general sample complexity analysis of vanilla policy gradient [101.16957584135767]
  Policy gradient (PG) is one of the most popular reinforcement learning (RL) problems. "vanilla" theoretical understanding of PG trajectory is one of the most popular methods for solving RL problems.
  arXiv  Detail & Related papers  (2021-07-23T19:38:17Z)
• Provably Correct Optimization and Exploration with Non-linear Policies [65.60853260886516]
  ENIAC is an actor-critic method that allows non-linear function approximation in the critic. We show that under certain assumptions, the learner finds a near-optimal policy in $O(poly(d))$ exploration rounds. We empirically evaluate this adaptation and show that it outperforms priors inspired by linear methods.
  arXiv  Detail & Related papers  (2021-03-22T03:16:33Z)
• Zeroth-order Deterministic Policy Gradient [116.87117204825105]
  We introduce Zeroth-order Deterministic Policy Gradient (ZDPG) ZDPG approximates policy-reward gradients via two-point evaluations of the $Q$function. New finite sample complexity bounds for ZDPG improve upon existing results by up to two orders of magnitude.
  arXiv  Detail & Related papers  (2020-06-12T16:52:29Z)

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.