Architecting and Visualizing Deep Reinforcement Learning Models
- URL: http://arxiv.org/abs/2112.01451v1
- Date: Thu, 2 Dec 2021 17:48:26 GMT
- Title: Architecting and Visualizing Deep Reinforcement Learning Models
- Authors: Alexander Neuwirth and Derek Riley
- Abstract summary: Deep Reinforcement Learning (DRL) is a theory that aims to teach computers how to communicate with each other.
In this paper, we present a new Atari Pong game environment, a policy gradient based DRL model, a real-time network visualization, and an interactive display to help build intuition and awareness of the mechanics of DRL inference.
- Score: 77.34726150561087
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: To meet the growing interest in Deep Reinforcement Learning (DRL), we sought
to construct a DRL-driven Atari Pong agent and accompanying visualization tool.
Existing approaches do not support the flexibility required to create an
interactive exhibit with easily-configurable physics and a human-controlled
player. Therefore, we constructed a new Pong game environment, discovered and
addressed a number of unique data deficiencies that arise when applying DRL to
a new environment, architected and tuned a policy gradient based DRL model,
developed a real-time network visualization, and combined these elements into
an interactive display to help build intuition and awareness of the mechanics
of DRL inference.
Related papers
- A Benchmark Environment for Offline Reinforcement Learning in Racing Games [54.83171948184851]
Offline Reinforcement Learning (ORL) is a promising approach to reduce the high sample complexity of traditional Reinforcement Learning (RL)
This paper introduces OfflineMania, a novel environment for ORL research.
It is inspired by the iconic TrackMania series and developed using the Unity 3D game engine.
arXiv Detail & Related papers (2024-07-12T16:44:03Z) - An Architecture for Deploying Reinforcement Learning in Industrial
Environments [3.18294468240512]
We present an OPC UA based Operational Technology (OT)-aware RL architecture.
We define an OPC UA information model allowing for a generalized plug-and-play like approach for exchanging the RL agent.
By means of solving a toy example, we show that this architecture can be used to determine the optimal policy.
arXiv Detail & Related papers (2023-06-02T10:22:01Z) - Making Offline RL Online: Collaborative World Models for Offline Visual
Reinforcement Learning [99.59728624855566]
This paper tries to build more flexible constraints for value estimation without impeding the exploration of potential advantages.
The key idea is to leverage off-the-shelf RL simulators, which can be easily interacted with in an online manner, as the "test bed" for offline policies.
We introduce CoWorld, a model-based RL approach that mitigates cross-domain discrepancies in state and reward spaces.
arXiv Detail & Related papers (2023-05-24T15:45:35Z) - Agent-Controller Representations: Principled Offline RL with Rich
Exogenous Information [49.06422815335159]
Learning to control an agent from data collected offline is vital for real-world applications of reinforcement learning (RL)
This paper introduces offline RL benchmarks offering the ability to study this problem.
We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time dependent process.
arXiv Detail & Related papers (2022-10-31T22:12:48Z) - Bridging the Gap to Real-World Object-Centric Learning [66.55867830853803]
We show that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way.
Our approach, DINOSAUR, significantly out-performs existing object-centric learning models on simulated data.
arXiv Detail & Related papers (2022-09-29T15:24:47Z) - Human-Level Reinforcement Learning through Theory-Based Modeling,
Exploration, and Planning [27.593497502386143]
Theory-Based Reinforcement Learning uses human-like intuitive theories to explore and model an environment.
We instantiate the approach in a video game playing agent called EMPA.
EMPA matches human learning efficiency on a suite of 90 Atari-style video games.
arXiv Detail & Related papers (2021-07-27T01:38:13Z) - Offline Reinforcement Learning from Images with Latent Space Models [60.69745540036375]
offline reinforcement learning (RL) refers to the problem of learning policies from a static dataset of environment interactions.
We build on recent advances in model-based algorithms for offline RL, and extend them to high-dimensional visual observation spaces.
Our approach is both tractable in practice and corresponds to maximizing a lower bound of the ELBO in the unknown POMDP.
arXiv Detail & Related papers (2020-12-21T18:28:17Z) - The Adversarial Resilience Learning Architecture for AI-based Modelling,
Exploration, and Operation of Complex Cyber-Physical Systems [0.0]
We describe the concept of Adversarial Learning (ARL) that formulates a new approach to complex environment checking and resilient operation.
The quintessence of ARL lies in both agents exploring the system and training each other without any domain knowledge.
Here, we introduce the ARL software architecture that allows to use a wide range of model-free as well as model-based DRL-based algorithms.
arXiv Detail & Related papers (2020-05-27T19:19:57Z)
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.