Automated Curriculum Learning for Embodied Agents: A Neuroevolutionary Approach

• URL: http://arxiv.org/abs/2102.08849v1
• Date: Wed, 17 Feb 2021 16:19:17 GMT
• Title: Automated Curriculum Learning for Embodied Agents: A Neuroevolutionary Approach
• Authors: Nicola Milano and Stefano Nolfi
• Abstract summary: We demonstrate how an evolutionary algorithm can be extended with a curriculum learning process that selects automatically the environmental conditions in which the evolving agents are evaluated. The results collected on two benchmark problems, that require to solve a task in significantly varying environmental conditions, demonstrate that the method proposed outperforms conventional algorithms and generates solutions that are robust to variations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We demonstrate how an evolutionary algorithm can be extended with a curriculum learning process that selects automatically the environmental conditions in which the evolving agents are evaluated. The environmental conditions are selected so to adjust the level of difficulty to the ability level of the current evolving agents and so to challenge the weaknesses of the evolving agents. The method does not require domain knowledge and does not introduce additional hyperparameters. The results collected on two benchmark problems, that require to solve a task in significantly varying environmental conditions, demonstrate that the method proposed outperforms conventional algorithms and generates solutions that are robust to variations

Related papers

• No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery [53.08822154199948]
  Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks. This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics. We develop a method that directly trains on scenarios with high learnability.
  arXiv  Detail & Related papers  (2024-08-27T14:31:54Z)
• Reinforcement Learning with Options and State Representation [105.82346211739433]
  This thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones. It addresses such goals by decomposing learning tasks in a hierarchical fashion known as Hierarchical Reinforcement Learning.
  arXiv  Detail & Related papers  (2024-03-16T08:30:55Z)
• HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments [93.94020724735199]
  HAZARD consists of three unexpected disaster scenarios, including fire, flood, and wind. This benchmark enables us to evaluate autonomous agents' decision-making capabilities across various pipelines.
  arXiv  Detail & Related papers  (2024-01-23T18:59:43Z)
• Act as You Learn: Adaptive Decision-Making in Non-Stationary Markov Decision Processes [5.276882857467777]
  We present a search algorithm called textitAdaptive Monte Carlo Tree Search (ADA-MCTS) We show that the agent can learn the updated dynamics of the environment over time and then act as it learns, i.e., if the agent is in a region of the state space about which it has updated knowledge, it can avoid being pessimistic.
  arXiv  Detail & Related papers  (2024-01-03T17:19:54Z)
• AGENT: An Adaptive Grouping Entrapping Method of Flocking Systems [4.922399029219211]
  This study proposes a distributed algorithm that makes agents' adaptive grouping entrap multiple targets. Agents make their own decisions about which targets to surround based on environmental information. The proposed strategies guarantee that the coordination of swarm agents develops the phenomenon of multiple targets entrapping at the swarm level.
  arXiv  Detail & Related papers  (2022-06-25T15:12:18Z)
• Robust Reinforcement Learning via Genetic Curriculum [5.421464476555662]
  Genetic curriculum is an algorithm that automatically identifies scenarios in which the agent currently fails and generates an associated curriculum. Our empirical studies show improvement in robustness over the existing state of the art algorithms, providing training curricula that result in agents being 2 - 8x times less likely to fail.
  arXiv  Detail & Related papers  (2022-02-17T01:14:20Z)
• Adaptability of Improved NEAT in Variable Environments [0.0]
  NeuroEvolution of Augmenting Topologies (NEAT) was a novel Genetic Algorithm (GA) when it was created, but has fallen aside with newer GAs outperforming it. This paper furthers the research on this subject by implementing various versions of improved NEAT in a variable environment. The improvements included, in every combination, are: recurrent connections, automatic feature selection, and increasing population size.
  arXiv  Detail & Related papers  (2021-10-22T15:33:51Z)
• Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design [121.73425076217471]
  We propose Unsupervised Environment Design (UED), where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid, solvable environments. We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED) Our experiments demonstrate that PAIRED produces a natural curriculum of increasingly complex environments, and PAIRED agents achieve higher zero-shot transfer performance when tested in highly novel environments.
  arXiv  Detail & Related papers  (2020-12-03T17:37:01Z)
• One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL [142.36621929739707]
  We show that learning diverse behaviors for accomplishing a task can lead to behavior that generalizes to varying environments. By identifying multiple solutions for the task in a single environment during training, our approach can generalize to new situations.
  arXiv  Detail & Related papers  (2020-10-27T17:41:57Z)
• Learning High-Level Policies for Model Predictive Control [54.00297896763184]
  Model Predictive Control (MPC) provides robust solutions to robot control tasks. We propose a self-supervised learning algorithm for learning a neural network high-level policy. We show that our approach can handle situations that are difficult for standard MPC.
  arXiv  Detail & Related papers  (2020-07-20T17:12:34Z)
• Learning to Switch Among Agents in a Team via 2-Layer Markov Decision Processes [41.04897149364321]
  We develop algorithms that, by learning to switch control between agents, allow existing reinforcement learning agents to operate under different automation levels. The total regret of our algorithm with respect to the optimal switching policy is sublinear in the number of learning steps. Simulation experiments in an obstacle avoidance task illustrate our theoretical findings and demonstrate that, by exploiting the specific structure of the problem, our proposed algorithm is superior to problem-agnostic algorithms.
  arXiv  Detail & Related papers  (2020-02-11T08:50:52Z)

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.