mlsanityData to 7 Oct 2026

Probabilistic Programming Bots in Intuitive Physics Game Play

arXiv 2104.01980 ↗First posted 5 Apr 2021cs.AI stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent findings suggest that humans deploy cognitive mechanism of physics simulation engines to simulate the physics of objects. We propose a framework for bots to deploy probabilistic programming tools for interacting with intuitive physics environments. The framework employs a physics simulation in a probabilistic way to infer about moves performed by an agent in a setting governed by Newtonian laws of motion. However, methods of probabilistic programs can be slow in such setting due to their need to generate many samples. We complement the model with a model-free approach to aid the sampling procedures in becoming more efficient through learning from experience during game playing. We present an approach where combining model-free approaches (a convolutional neural network in our model) and model-based approaches (probabilistic physics simulation) is able to achieve what neither could alone. This way the model outperforms an all model-free or all model-based approach. We discuss a case study showing empirical results of the performance of the model on the game of Flappy Bird.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 5 Apr 2021.

Builds on

18 of 32 references.

References · 18

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2015Trust Region Policy Optimizationcited by 2,503
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  5. 2017Deep Reinforcement Learning that Matterscited by 727
  6. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  7. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  8. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  9. 2017Learning Explanatory Rules from Noisy Datacited by 210
  10. 2016Learning to Poke by Poking: Experiential Learning of Intuitive Physicscited by 152
  11. 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 149
  12. 2019PHYRE: A New Benchmark for Physical Reasoningcited by 137
6 more
  1. 2017Visual Interaction Networkscited by 94
  2. 2019CoPhy: Counterfactual Learning of Physical Dynamicscited by 80
  3. 2016Learning Physical Intuition of Block Towers by Examplecited by 66
  4. 2017Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physicscited by 57
  5. 2017Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learningcited by 27
  6. 2020Predicting the Physical Dynamics of Unseen 3D Objectscited by 6

Built on by

Not cited yet.