Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts

• URL: http://arxiv.org/abs/2211.05500v1
• Date: Thu, 10 Nov 2022 11:48:10 GMT
• Title: Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts
• Authors: Patrik Hammersborg and Inga Str\"umke
• Abstract summary: We show a method for probing which concepts self-learning agents internalise in the course of their training. For demonstration, we use a chess playing agent in a fast and light environment developed specifically to be suitable for research groups.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-trained autonomous agents developed using machine learning are showing great promise in a variety of control settings, perhaps most remarkably in applications involving autonomous vehicles. The main challenge associated with self-learned agents in the form of deep neural networks, is their black-box nature: it is impossible for humans to interpret deep neural networks. Therefore, humans cannot directly interpret the actions of deep neural network based agents, or foresee their robustness in different scenarios. In this work, we demonstrate a method for probing which concepts self-learning agents internalise in the course of their training. For demonstration, we use a chess playing agent in a fast and light environment developed specifically to be suitable for research groups without access to enormous computational resources or machine learning models.

Related papers

• Brain-Inspired Computational Intelligence via Predictive Coding [89.6335791546526]
  Predictive coding (PC) has shown promising performance in machine intelligence tasks. PC can model information processing in different brain areas, can be used in cognitive control and robotics.
  arXiv  Detail & Related papers  (2023-08-15T16:37:16Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction [50.79827516897913]
  We introduce an interpretable paradigm for trajectory prediction that distributes the uncertainty among semantic concepts. We validate our approach on real-world autonomous driving data, demonstrating superior performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-11-16T06:28:20Z)
• Neurosymbolic hybrid approach to driver collision warning [64.02492460600905]
  There are two main algorithmic approaches to autonomous driving systems. Deep learning alone has achieved state-of-the-art results in many areas. But sometimes it can be very difficult to debug if the deep learning model doesn't work.
  arXiv  Detail & Related papers  (2022-03-28T20:29:50Z)
• Probe-Based Interventions for Modifying Agent Behavior [4.324022085722613]
  We develop a method for updating representations in pre-trained neural nets according to externally-specified properties. In experiments, we show how our method may be used to improve human-agent team performance for a variety of neural networks.
  arXiv  Detail & Related papers  (2022-01-26T19:14:00Z)
• Automating Privilege Escalation with Deep Reinforcement Learning [71.87228372303453]
  In this work, we exemplify the potential threat of malicious actors using deep reinforcement learning to train automated agents. We present an agent that uses a state-of-the-art reinforcement learning algorithm to perform local privilege escalation. Our agent is usable for generating realistic attack sensor data for training and evaluating intrusion detection systems.
  arXiv  Detail & Related papers  (2021-10-04T12:20:46Z)
• Brain-Inspired Deep Imitation Learning for Autonomous Driving Systems [0.38673630752805443]
  Humans have a strong generalisation ability which is beneficial from the structural and functional asymmetry of the two sides of the brain. Here, we design dual Neural Circuit Policy (NCP) architectures in deep neural networks based on the asymmetry of human neural networks. Experimental results demonstrate that our brain-inspired method outperforms existing methods regarding generalisation when dealing with unseen data.
  arXiv  Detail & Related papers  (2021-07-30T14:21:46Z)
• Backprop-Free Reinforcement Learning with Active Neural Generative Coding [84.11376568625353]
  We propose a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. We develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. The robust performance of our agent offers promising evidence that a backprop-free approach for neural inference and learning can drive goal-directed behavior.
  arXiv  Detail & Related papers  (2021-07-10T19:02:27Z)
• Sparse Training Theory for Scalable and Efficient Agents [5.71531053864579]
  Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Traditional deep learning approaches make use of cloud computing facilities and do not scale well to autonomous agents with low computational resources. This paper discusses sparse training state-of-the-art, its challenges and limitations while introducing a couple of new theoretical research directions.
  arXiv  Detail & Related papers  (2021-03-02T10:48:29Z)
• Self-explaining AI as an alternative to interpretable AI [0.0]
  Double descent indicates that deep neural networks operate by smoothly interpolating between data points. Neural networks trained on complex real world data are inherently hard to interpret and prone to failure if asked to extrapolate. Self-explaining AIs are capable of providing a human-understandable explanation along with confidence levels for both the decision and explanation.
  arXiv  Detail & Related papers  (2020-02-12T18:50:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.