Results 1 -
4 of
4
Sample Complexity of Multi-task Reinforcement Learning
"... Transferring knowledge across a sequence of reinforcement-learning tasks is challenging, and has a number of important applications. Though there is encouraging empirical evidence that transfer can improve performance in subsequent reinforcement-learning tasks, there has been very little theoretical ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
(Show Context)
Transferring knowledge across a sequence of reinforcement-learning tasks is challenging, and has a number of important applications. Though there is encouraging empirical evidence that transfer can improve performance in subsequent reinforcement-learning tasks, there has been very little theoretical analysis. In this paper, we introduce a new multi-task algorithm for a sequence of reinforcement-learning tasks when each task is sampled independently from (an unknown) distribution over a finite set of Markov decision processes whose parameters are initially unknown. For this setting, we prove under certain assumptions that the per-task sample complexity of exploration is reduced significantly due to transfer compared to standard single-task algorithms. Our multi-task algorithm also has the desired characteristic that it is guaranteed not to exhibit negative transfer: in the worst case its per-task sample complexity is comparable to the corresponding single-task algorithm. 1
Reinforcement Learning with Multi-Fidelity Simulators
"... Abstract — We present a framework for reinforcement learn-ing (RL) in a scenario where multiple simulators are available with decreasing amounts of fidelity to the real-world learning scenario. Our framework is designed to limit the number of samples used in each successively higher-fidelity/cost si ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
(Show Context)
Abstract — We present a framework for reinforcement learn-ing (RL) in a scenario where multiple simulators are available with decreasing amounts of fidelity to the real-world learning scenario. Our framework is designed to limit the number of samples used in each successively higher-fidelity/cost simulator by allowing the agent to choose to run trajectories at the lowest level that will still provide it with information. The approach transfers state-action Q-values from lower-fidelity models as heuristics for the “Knows What It Knows ” family of RL algorithms, which is applicable over a wide range of possible dynamics and reward representations. Theoretical proofs of the framework’s sample complexity are given and empirical results are demonstrated on a remote controlled car with multiple simulators. The approach allows RL algorithms to find near-optimal policies for the real world with fewer expensive real-world samples than previous transfer approaches or learning without simulators. I.
Real-World Reinforcement Learning via Multi-Fidelity Simulators
"... Abstract—Reinforcement learning (RL) can be a tool for designing policies and controllers for robotic systems. However, the cost of real-world samples remains prohibitive as many RL algorithms require a large number of samples before learning useful policies. Simulators are one way to decrease the n ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Reinforcement learning (RL) can be a tool for designing policies and controllers for robotic systems. However, the cost of real-world samples remains prohibitive as many RL algorithms require a large number of samples before learning useful policies. Simulators are one way to decrease the number of required real-world samples, but imperfect models make deciding when and how to trust samples from a simulator difficult. We present a framework for efficient RL in a scenario where multiple simulators of a target task are available, each with varying levels of fidelity. The framework is designed to limit the number of samples used in each successively higher-fidelity/cost simulator by allowing a learning agent to choose to run trajectories at the lowest level simulator that will still provide it with useful information. Theoretical proofs of the framework’s sample complexity are given and empirical results are demonstrated on a remote controlled car with multiple simulators. The approach enables RL algorithms to find near-optimal policies in a physical robot domain with fewer expensive real-world samples than previous transfer approaches or learning without simulators.
PAC-inspired Option Discovery in Lifelong Reinforcement Learning
"... A key goal of AI is to create lifelong learn-ing agents that can leverage prior experience to improve performance on later tasks. In reinforcement-learning problems, one way to summarize prior experience for future use is through options, which are temporally extended actions (subpolicies) for how t ..."
Abstract
- Add to MetaCart
A key goal of AI is to create lifelong learn-ing agents that can leverage prior experience to improve performance on later tasks. In reinforcement-learning problems, one way to summarize prior experience for future use is through options, which are temporally extended actions (subpolicies) for how to behave. Op-tions can then be used to potentially accelerate learning in new reinforcement learning tasks. In this work, we provide the first formal analysis of the sample complexity, a measure of learning speed, of reinforcement learning with options. This analysis helps shed light on some interesting prior empirical results on when and how options may accelerate learning. We then quantify the benefit of options in reducing sample complexity of a lifelong learning agent. Finally, the new the-oretical insights inspire a novel option-discovery algorithm that aims at minimizing overall sample complexity in lifelong reinforcement learning. 1.
