Learning finite state representations of recurrent policy networks
Recurrent neural networks (RNNs) are an effective representation of control policies for a
wide range of reinforcement and imitation learning problems. RNN policies, however, are …
wide range of reinforcement and imitation learning problems. RNN policies, however, are …
Re-understanding finite-state representations of recurrent policy networks
We introduce an approach for understanding control policies represented as recurrent
neural networks. Recent work has approached this problem by transforming such recurrent …
neural networks. Recent work has approached this problem by transforming such recurrent …
[HTML][HTML] Investigating the properties of neural network representations in reinforcement learning
In this paper we investigate the properties of representations learned by deep reinforcement
learning systems. Much of the early work on representations for reinforcement learning …
learning systems. Much of the early work on representations for reinforcement learning …
On learning to think: Algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models
J Schmidhuber - arXiv preprint arXiv:1511.09249, 2015 - arxiv.org
This paper addresses the general problem of reinforcement learning (RL) in partially
observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned …
observable environments. In 2013, our large RL recurrent neural networks (RNNs) learned …
A neurally plausible model learns successor representations in partially observable environments
Animals need to devise strategies to maximize returns while interacting with their
environment based on incoming noisy sensory observations. Task-relevant states, such as …
environment based on incoming noisy sensory observations. Task-relevant states, such as …
Reinforcement learning with echo state networks
Function approximators are often used in reinforcement learning tasks with large or
continuous state spaces. Artificial neural networks, among them recurrent neural networks …
continuous state spaces. Artificial neural networks, among them recurrent neural networks …
Verifiable reinforcement learning via policy extraction
While deep reinforcement learning has successfully solved many challenging control tasks,
its real-world applicability has been limited by the inability to ensure the safety of learned …
its real-world applicability has been limited by the inability to ensure the safety of learned …
Recurrent reinforcement learning: a hybrid approach
Successful applications of reinforcement learning in real-world problems often require
dealing with partially observable states. It is in general very challenging to construct and …
dealing with partially observable states. It is in general very challenging to construct and …
When to use parametric models in reinforcement learning?
HP Van Hasselt, M Hessel… - Advances in Neural …, 2019 - proceedings.neurips.cc
We examine the question of when and how parametric models are most useful in
reinforcement learning. In particular, we look at commonalities and differences between …
reinforcement learning. In particular, we look at commonalities and differences between …
[PDF][PDF] Using Predictive Representations to Improve Generalization in Reinforcement Learning.
The predictive representations hypothesis holds that particularly good generalization will
result from representing the state of the world in terms of predictions about possible future …
result from representing the state of the world in terms of predictions about possible future …