TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions

by   Gellért Weisz, et al.

We consider the minimax query complexity of online planning with a generative model in fixed-horizon Markov decision processes (MDPs) with linear function approximation. Following recent works, we consider broad classes of problems where either (i) the optimal value function v^⋆ or (ii) the optimal action-value function q^⋆ lie in the linear span of some features; or (iii) both v^⋆ and q^⋆ lie in the linear span when restricted to the states reachable from the starting state. Recently, Weisz et al. (2021b) showed that under (ii) the minimax query complexity of any planning algorithm is at least exponential in the horizon H or in the feature dimension d when the size A of the action set can be chosen to be exponential in min(d,H). On the other hand, for the setting (i), Weisz et al. (2021a) introduced TensorPlan, a planner whose query cost is polynomial in all relevant quantities when the number of actions is fixed. Among other things, these two works left open the question whether polynomial query complexity is possible when A is subexponential in min(d,H). In this paper we answer this question in the negative: we show that an exponentially large lower bound holds when A=Ω(min(d^1/4,H^1/2)), under either (i), (ii) or (iii). In particular, this implies a perhaps surprising exponential separation of query complexity compared to the work of Du et al. (2021) who prove a polynomial upper bound when (iii) holds for all states. Furthermore, we show that the upper bound of TensorPlan can be extended to hold under (iii) and, for MDPs with deterministic transitions and stochastic rewards, also under (ii).


On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function

We consider the problem of local planning in fixed-horizon Markov Decisi...

Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions

We consider the problem of local planning in fixed-horizon Markov Decisi...

On the Sample Complexity of Batch Reinforcement Learning with Policy-Induced Data

We study the fundamental question of the sample complexity of learning a...

An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap

A fundamental question in the theory of reinforcement learning is: suppo...

Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally

We study the statistical limits of Imitation Learning (IL) in episodic M...

The Fine-Grained Complexity of Computing the Tutte Polynomial of a Linear Matroid

We show that computing the Tutte polynomial of a linear matroid of dimen...

From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses

We propose the Bayes-UCBVI algorithm for reinforcement learning in tabul...

Please sign up or login with your details

Forgot password? Click here to reset