Discrete-to-Deep Supervised Policy Learning

• URL: http://arxiv.org/abs/2005.02057v1
• Date: Tue, 5 May 2020 10:49:00 GMT
• Title: Discrete-to-Deep Supervised Policy Learning
• Authors: Budi Kurniawan, Peter Vamplew, Michael Papasimeon, Richard Dazeley, Cameron Foale
• Abstract summary: This paper proposes Discrete-to-Deep Supervised Policy Learning (D2D-SPL) for training neural networks in reinforcement learning. D2D-SPL uses a single agent, needs no experience replay and learns much faster than state-of-the-art methods.
• Score: 2.212418070140923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. For years, scholars have got around this by employing experience replay or an asynchronous parallel-agent system. This paper proposes Discrete-to-Deep Supervised Policy Learning (D2D-SPL) for training neural networks in RL. D2D-SPL discretises the continuous state space into discrete states and uses actor-critic to learn a policy. It then selects from each discrete state an input value and the action with the highest numerical preference as an input/target pair. Finally it uses input/target pairs from all discrete states to train a classifier. D2D-SPL uses a single agent, needs no experience replay and learns much faster than state-of-the-art methods. We test our method with two RL environments, the Cartpole and an aircraft manoeuvring simulator.

Related papers

• Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories [33.872433985210876]
  Scaling vision-language-action (VLA) model pre-training requires large volumes of diverse, high-quality manipulation trajectories.<n>We propose Discover, Lea rn and Reinforce, which generates multiple distinct, high-success behavioral patterns for VLA pretraining.<n>When adapted to unseen downstream task suites, VLA models pretrained on our diverse RL data surpass counterparts trained on equal-sized standard RL datasets.
  arXiv  Detail & Related papers  (2025-11-24T07:54:49Z)
• End-to-end RL Improves Dexterous Grasping Policies [64.8476328230578]
  This work explores techniques to scale up image-based end-to-end learning for dexterous grasping with an arm + hand system.<n>We train and distill both depth and state-based policies into stereo RGB networks and show that depth distillation leads to better results, both in simulation and reality.
  arXiv  Detail & Related papers  (2025-09-19T21:21:29Z)
• Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms [4.127488674019288]
  Post-training for large language models co-locates trajectory sampling and policy optimisation on the same GPU cluster.<n>We present Echo, the RL system that cleanly decouples these two phases across heterogeneous "inference" and "training" swarms.
  arXiv  Detail & Related papers  (2025-08-07T13:37:04Z)
• Diffusion Policies creating a Trust Region for Offline Reinforcement Learning [66.17291150498276]
  We introduce a dual policy approach, Diffusion Trusted Q-Learning (DTQL), which comprises a diffusion policy for pure behavior cloning and a practical one-step policy. DTQL eliminates the need for iterative denoising sampling during both training and inference, making it remarkably computationally efficient. We show that DTQL could not only outperform other methods on the majority of the D4RL benchmark tasks but also demonstrate efficiency in training and inference speeds.
  arXiv  Detail & Related papers  (2024-05-30T05:04:33Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)
• Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity [8.068886870457561]
  Deep Reinforcement Learning (DRL) has exhibited efficacy in resolving the Local Path Planning (LPP) problem. Such application in the real world is immensely limited due to the deficient training efficiency and generalization capability of DRL. A solution named Color is proposed, which consists of an Actor-Sharer-Learner (ASL) training framework and a mobile robot-oriented simulator Sparrow.
  arXiv  Detail & Related papers  (2023-05-07T03:39:31Z)
• Visual processing in context of reinforcement learning [0.0]
  This thesis introduces three different representation learning algorithms that have access to different subsets of the data sources that traditional RL algorithms use. We conclude that including unsupervised representation learning in RL problem-solving pipelines can speed up learning.
  arXiv  Detail & Related papers  (2022-08-26T09:30:51Z)
• Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning [105.70602423944148]
  We propose a novel method, called value-consistent representation learning (VCR), to learn representations that are directly related to decision-making. Instead of aligning this imagined state with a real state returned by the environment, VCR applies a $Q$-value head on both states and obtains two distributions of action values. It has been demonstrated that our methods achieve new state-of-the-art performance for search-free RL algorithms.
  arXiv  Detail & Related papers  (2022-06-25T03:02:25Z)
• 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)
• RvS: What is Essential for Offline RL via Supervised Learning? [77.91045677562802]
  Recent work has shown that supervised learning alone, without temporal difference (TD) learning, can be remarkably effective for offline RL. In every environment suite we consider simply maximizing likelihood with two-layer feedforward is competitive. They also probe the limits of existing RvS methods, which are comparatively weak on random data.
  arXiv  Detail & Related papers  (2021-12-20T18:55:16Z)
• Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches [0.0]
  We focus on the use of co-training, a semi-supervised learning (SSL) method, for obtaining self-labeled object bounding boxes (BBs) In particular, we assess the goodness of multi-modal co-training by relying on two different views of an image, namely, appearance (RGB) and estimated depth (D) Our results suggest that in a standard SSL setting (no domain shift, a few human-labeled data) and under virtual-to-real domain shift (many virtual-world labeled data, no human-labeled data) multi-modal co-training outperforms single-modal.
  arXiv  Detail & Related papers  (2021-04-23T14:13:59Z)
• Learn Dynamic-Aware State Embedding for Transfer Learning [0.8756822885568589]
  We consider the setting where all tasks (MDPs) share the same environment dynamic except reward function. In this setting, the MDP dynamic is a good knowledge to transfer, which can be inferred by uniformly random policy. We observe that the binary MDP dynamic can be inferred from trajectories of any policy which avoids the need of uniform random policy.
  arXiv  Detail & Related papers  (2021-01-06T19:07:31Z)
• Decoupling Representation Learning from Reinforcement Learning [89.82834016009461]
  We introduce an unsupervised learning task called Augmented Temporal Contrast (ATC) ATC trains a convolutional encoder to associate pairs of observations separated by a short time difference. In online RL experiments, we show that training the encoder exclusively using ATC matches or outperforms end-to-end RL.
  arXiv  Detail & Related papers  (2020-09-14T19:11:13Z)

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.