Design of Artificial Intelligence Agents for Games using Deep Reinforcement Learning

by   Andrei Claudiu Roibu, et al.

In order perform a large variety of tasks and to achieve human-level performance in complex real-world environments, Artificial Intelligence (AI) Agents must be able to learn from their past experiences and gain both knowledge and an accurate representation of their environment from raw sensory inputs. Traditionally, AI agents have suffered from difficulties in using only sensory inputs to obtain a good representation of their environment and then mapping this representation to an efficient control policy. Deep reinforcement learning algorithms have provided a solution to this issue. In this study, the performance of different conventional and novel deep reinforcement learning algorithms was analysed. The proposed method utilises two types of algorithms, one trained with a variant of Q-learning (DQN) and another trained with SARSA learning (DSN) to assess the feasibility of using direct feedback alignment, a novel biologically plausible method for back-propagating the error. These novel agents, alongside two similar agents trained with the conventional backpropagation algorithm, were tested by using the OpenAI Gym toolkit on several classic control theory problems and Atari 2600 video games. The results of this investigation open the way into new, biologically-inspired deep reinforcement learning algorithms, and their implementation on neuromorphic hardware.



There are no comments yet.



Emphatic Algorithms for Deep Reinforcement Learning

Off-policy learning allows us to learn about possible policies of behavi...

Deep Learning and the Global Workspace Theory

Recent advances in deep learning have allowed Artificial Intelligence (A...

Biomechanic Posture Stabilisation via Iterative Training of Multi-policy Deep Reinforcement Learning Agents

It is not until we become senior citizens do we recognise how much we to...

Automatic Bridge Bidding Using Deep Reinforcement Learning

Bridge is among the zero-sum games for which artificial intelligence has...

Concept Learning in Deep Reinforcement Learning

Deep reinforcement learning techniques have shown to be a promising path...

High Performance Across Two Atari Paddle Games Using the Same Perceptual Control Architecture Without Training

Deep reinforcement learning (DRL) requires large samples and a long trai...

EBIC: an artificial intelligence-based parallel biclustering algorithm for pattern discovery

In this paper a novel biclustering algorithm based on artificial intelli...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.