Goto

Collaborating Authors

 Reinforcement Learning


Neurally Plausible Reinforcement Learning of Working Memory Tasks

Neural Information Processing Systems

A key function of brains is undoubtedly the abstraction and maintenance of information from the environment for later use. Neurons in association cortex play an important role in this process: during learning these neurons become tuned to relevant features and represent the information that is required later as a persistent elevation of their activity. It is however not well known how these neurons acquire their task-relevant tuning. Here we introduce a biologically plausible learning scheme that explains how neurons become selective for relevant information when animals learn by trial and error. We propose that the action selection stage feeds back attentional signals to earlier processing levels.


Transferring Expectations in Model-based Reinforcement Learning

Neural Information Processing Systems

We study how to automatically select and adapt multiple abstractions or representations of the world to support model-based reinforcement learning. We address the challenges of transfer learning in heterogeneous environments with varying tasks. We present an efficient, online framework that, through a sequence of tasks, learns a set of relevant representations to be used in future tasks. Without pre-defined mapping strategies, we introduce a general approach to support transfer learning across different state spaces. We demonstrate the potential impact of our system through improved jumpstart and faster convergence to near optimum policy in two benchmark domains.


Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

Neural Information Processing Systems

Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way. Unfortunately, finding the resulting Bayes-optimal policies is notoriously taxing, since the search space becomes enormous. In this paper we introduce a tractable, sample-based method for approximate Bayes-optimal planning which exploits Monte-Carlo tree search. Our approach outperformed prior Bayesian model-based RL algorithms by a significant margin on several well-known benchmark problems -- because it avoids expensive applications of Bayes rule within the search tree by lazily sampling models from the current beliefs. We illustrate the advantages of our approach by showing it working in an infinite state space domain which is qualitatively out of reach of almost all previous work in Bayesian exploration.


On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization

Neural Information Processing Systems

The ability to learn a policy for a sequential decision problem with continuous state space using on-line data is a long-standing challenge. This paper presents a new reinforcement-learning algorithm, called iKBSF, which extends the benefits of kernel-based learning to the on-line scenario. As a kernel-based method, the proposed algorithm is stable and has good convergence properties. However, unlike other similar algorithms,iKBSF's space complexity is independent of the number of sample transitions, and as a result it can process an arbitrary amount of data. We present theoretical results showing that iKBSF can approximate (to any level of accuracy) the value function that would be learned by an equivalent batch non-parametric kernel-based reinforcement learning approximator.


Nonparametric Bayesian Inverse Reinforcement Learning for Multiple Reward Functions

Neural Information Processing Systems

We present a nonparametric Bayesian approach to inverse reinforcement learning (IRL) for multiple reward functions. Most previous IRL algorithms assume that the behaviour data is obtained from an agent who is optimizing a single reward function, but this assumption is hard to be met in practice. Our approach is based on integrating the Dirichlet process mixture model into Bayesian IRL. We provide an efficient Metropolis-Hastings sampling algorithm utilizing the gradient of the posterior to estimate the underlying reward functions, and demonstrate that our approach outperforms the previous ones via experiments on a number of problem domains.


Policy Shaping: Integrating Human Feedback with Reinforcement Learning

Neural Information Processing Systems

A long term goal of Interactive Reinforcement Learning is to incorporate non-expert human feedback to solve complex tasks. State-of-the-art methods have approached this problem by mapping human information to reward and value signals to indicate preferences and then iterating over them to compute the necessary control policy. In this paper we argue for an alternate, more effective characterization of human feedback: Policy Shaping. We introduce Advise, a Bayesian approach that attempts to maximize the information gained from human feedback by utilizing it as direct labels on the policy. We compare Advise to state-of-the-art approaches and highlight scenarios where it outperforms them and importantly is robust to infrequent and inconsistent human feedback.


Projected Natural Actor-Critic

Neural Information Processing Systems

Natural actor-critics are a popular class of policy search algorithms for finding locally optimal policies for Markov decision processes. In this paper we address a drawback of natural actor-critics that limits their real-world applicability - their lack of safety guarantees. We present a principled algorithm for performing natural gradient descent over a constrained domain. In the context of reinforcement learning, this allows for natural actor-critic algorithms that are guaranteed to remain within a known safe region of policy space. While deriving our class of constrained natural actor-critic algorithms, which we call Projected Natural Actor-Critics (PNACs), we also elucidate the relationship between natural gradient descent and mirror descent.


Optimism and Delays in Episodic Reinforcement Learning

arXiv.org Artificial Intelligence

There are many algorithms for regret minimisation in episodic reinforcement learning. This problem is well-understood from a theoretical perspective, providing that the sequences of states, actions and rewards associated with each episode are available to the algorithm updating the policy immediately after every interaction with the environment. However, feedback is almost always delayed in practice. In this paper, we study the impact of delayed feedback in episodic reinforcement learning from a theoretical perspective and propose two general-purpose approaches to handling the delays. The first involves updating as soon as new information becomes available, whereas the second waits before using newly observed information to update the policy. For the class of optimistic algorithms and either approach, we show that the regret increases by an additive term involving the number of states, actions, episode length, the expected delay and an algorithm-dependent constant. We empirically investigate the impact of various delay distributions on the regret of optimistic algorithms to validate our theoretical results.


AMS-DRL: Learning Multi-Pursuit Evasion for Safe Targeted Navigation of Drones

arXiv.org Artificial Intelligence

Safe navigation of drones in the presence of adversarial physical attacks from multiple pursuers is a challenging task. This paper proposes a novel approach, asynchronous multi-stage deep reinforcement learning (AMS-DRL), to train an adversarial neural network that can learn from the actions of multiple pursuers and adapt quickly to their behavior, enabling the drone to avoid attacks and reach its target. Our approach guarantees convergence by ensuring Nash Equilibrium among agents from the game-theory analysis. We evaluate our method in extensive simulations and show that it outperforms baselines with higher navigation success rates. We also analyze how parameters such as the relative maximum speed affect navigation performance. Furthermore, we have conducted physical experiments and validated the effectiveness of the trained policies in real-time flights. A success rate heatmap is introduced to elucidate how spatial geometry influences navigation outcomes. Project website: https://github.com/NTU-UAVG/AMS-DRL-for-Pursuit-Evasion.


UAV Obstacle Avoidance by Human-in-the-Loop Reinforcement in Arbitrary 3D Environment

arXiv.org Artificial Intelligence

This paper focuses on the continuous control of the unmanned aerial vehicle (UAV) based on a deep reinforcement learning method for a large-scale 3D complex environment. The purpose is to make the UAV reach any target point from a certain starting point, and the flying height and speed are variable during navigation. In this work, we propose a deep reinforcement learning (DRL)-based method combined with human-in-the-loop, which allows the UAV to avoid obstacles automatically during flying. We design multiple reward functions based on the relevant domain knowledge to guide UAV navigation. The role of human-in-the-loop is to dynamically change the reward function of the UAV in different situations to suit the obstacle avoidance of the UAV better. We verify the success rate and average step size on urban, rural, and forest scenarios, and the experimental results show that the proposed method can reduce the training convergence time and improve the efficiency and accuracy of navigation tasks. The code is available on the website https://github.com/Monnalo/UAV_navigation.