Discovering Reinforcement Learning Algorithms

• URL: http://arxiv.org/abs/2007.08794v3
• Date: Tue, 5 Jan 2021 12:44:56 GMT
• Title: Discovering Reinforcement Learning Algorithms
• Authors: Junhyuk Oh, Matteo Hessel, Wojciech M. Czarnecki, Zhongwen Xu, Hado van Hasselt, Satinder Singh, David Silver
• Abstract summary: Reinforcement learning algorithms update an agent's parameters according to one of several possible rules. This paper introduces a new meta-learning approach that discovers an entire update rule. It includes both 'what to predict' (e.g. value functions) and 'how to learn from it' by interacting with a set of environments.
• Score: 53.72358280495428
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient algorithms, or algorithms that are better adapted to specific environments. Although there have been prior attempts at addressing this significant scientific challenge, it remains an open question whether it is feasible to discover alternatives to fundamental concepts of RL such as value functions and temporal-difference learning. This paper introduces a new meta-learning approach that discovers an entire update rule which includes both 'what to predict' (e.g. value functions) and 'how to learn from it' (e.g. bootstrapping) by interacting with a set of environments. The output of this method is an RL algorithm that we call Learned Policy Gradient (LPG). Empirical results show that our method discovers its own alternative to the concept of value functions. Furthermore it discovers a bootstrapping mechanism to maintain and use its predictions. Surprisingly, when trained solely on toy environments, LPG generalises effectively to complex Atari games and achieves non-trivial performance. This shows the potential to discover general RL algorithms from data.

Related papers

• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning [3.194414753332705]
  We show that learning inapplicable actions greatly improves the sample efficiency of RL algorithms. Thanks to the transferability of the knowledge acquired, it can be reused in other tasks and domains to make the learning process more efficient.
  arXiv  Detail & Related papers  (2022-11-28T17:45:39Z)
• Discovered Policy Optimisation [17.458523575470384]
  We explore the Mirror Learning space by meta-learning a "drift" function. We refer to the immediate result as Learnt Policy optimisation (LPO) By analysing LPO we gain original insights into policy optimisation which we use to formulate a novel, closed-form RL algorithm, Discovered Policy optimisation (DPO)
  arXiv  Detail & Related papers  (2022-10-11T17:32:11Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)
• The Information Geometry of Unsupervised Reinforcement Learning [133.20816939521941]
  Unsupervised skill discovery is a class of algorithms that learn a set of policies without access to a reward function. We show that unsupervised skill discovery algorithms do not learn skills that are optimal for every possible reward function.
  arXiv  Detail & Related papers  (2021-10-06T13:08:36Z)
• Emphatic Algorithms for Deep Reinforcement Learning [43.17171330951343]
  Temporal difference learning algorithms can become unstable when combined with function approximation and off-policy sampling. Emphatic temporal difference (ETD($lambda$) algorithm ensures convergence in the linear case by appropriately weighting the TD($lambda$) updates. We show that naively adapting ETD($lambda$) to popular deep reinforcement learning algorithms, which use forward view multi-step returns, results in poor performance.
  arXiv  Detail & Related papers  (2021-06-21T12:11:39Z)
• Evolving Reinforcement Learning Algorithms [186.62294652057062]
  We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
  arXiv  Detail & Related papers  (2021-01-08T18:55:07Z)
• Meta-Gradient Reinforcement Learning with an Objective Discovered Online [54.15180335046361]
  We propose an algorithm based on meta-gradient descent that discovers its own objective, flexibly parameterised by a deep neural network. Because the objective is discovered online, it can adapt to changes over time. On the Atari Learning Environment, the meta-gradient algorithm adapts over time to learn with greater efficiency.
  arXiv  Detail & Related papers  (2020-07-16T16:17:09Z)

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.