paper-with-me

홈 › Papers

On the Value of Interaction and Function Approximation in Imitation Learning

2021-12-01 · NeurIPS 2021 12 · Nived Rajaraman, Yanjun Han, Lin Yang, Jingbo Liu, Jiantao Jiao, Kannan Ramchandran

We study the statistical guarantees for the Imitation Learning (IL) problem in episodic MDPs.Rajaraman et al. (2020) show an information theoretic lower bound that in the worst case, a learner which can even actively query the expert policy suffers from a suboptimality growing quadratically in the length of the horizon, $H$. We study imitation learning under the $\mu$-recoverability assumption of Ross et al. (2011) which assumes that the difference in the $Q$-value under the expert policy across different actions in a state do not deviate beyond $\mu$ from the maximum. We show that the reduction proposed by Ross et al. (2010) is statistically optimal: the resulting algorithm upon interacting with the MDP for $N$ episodes results in a suboptimality bound of $\widetilde{\mathcal{O}} \left( \mu |\mathcal{S}| H / N \right)$ which we show is optimal up to log-factors. In contrast, we show that any algorithm which does not interact with the MDP and uses an offline dataset of $N$ expert trajectories must incur suboptimality growing as $\gtrsim |\mathcal{S}| H^2/N$ even under the $\mu$-recoverability assumption. This establishes a clear and provable separation of the minimax rates between the active setting and the no-interaction setting. We also study IL with linear function approximation. When the expert plays actions according to a linear classifier of known state-action features, we use the reduction to multi-class classification to show that with high probability, the suboptimality of behavior cloning is $\widetilde{O}(dH^2/N)$ given $N$ rollouts from the optimal policy. This is optimal up to log-factors but can be improved to $\widetilde{O}(dH/N)$ if we have a linear expert with parameter-sharing across time steps. In contrast, when the MDP transition structure is known to the learner such as in the case of simulators, we demonstrate fundamental differences compared to the tabular setting in terms of the performance of an optimal algorithm, Mimic-MD (Rajaraman et al. (2020)) when extended to the function approximation setting. Here, we introduce a new problem called confidence set linear classification, that can be used to construct sample-efficient IL algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningMulti-class Classification

Similar Papers 제목 키워드 기반

Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension

2020-05-21 · NeurIPS 2020 12 · Ruosong Wang, Ruslan Salakhutdinov, Lin F. Yang

Value function approximation has demonstrated phenomenal empirical success in reinforcement learning (RL). Nevertheless, despite a handful of recent progress on developing theory for RL with linear function approximation…

Reinforcement Learning (RL)

C-CoCoA: A Continuous Cooperative Constraint Approximation Algorithm to Solve Functional DCOPs

2020-02-27 · Amit Sarker, Abdullahil Baki Arif, Moumita Choudhury, Md. Mosaddek Khan

Distributed Constraint Optimization Problems (DCOPs) have been widely used to coordinate interactions (i.e. constraints) in cooperative multi-agent systems. The traditional DCOP model assumes that variables owned by the …

Representation Learning on Graphs: A Reinforcement Learning Application

2019-01-16 · Sephora Madjiheurem, Laura Toni

In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation Learning

Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods

2024-07-13 · Riccardo De Santi, Manish Prajapat, Andreas Krause

In classic Reinforcement Learning (RL), the agent maximizes an additive objective of the visited states, e.g., a value function. Unfortunately, objectives of this type cannot model many real-world applications such as ex…

Imitation LearningReinforcement Learning (RL)

Improving Deep Policy Gradients with Value Function Search

2023-02-20 · Enrico Marchesini, Christopher Amato

Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates. However, value function approximation gets stuck in local opti…

continuous-controlContinuous ControlValue prediction