Learn to Interpret Atari Agents

• URL: http://arxiv.org/abs/1812.11276v3
• Date: Wed, 5 Apr 2023 20:53:34 GMT
• Title: Learn to Interpret Atari Agents
• Authors: Zhao Yang and Song Bai and Li Zhang and Philip H.S. Torr
• Abstract summary: Region-sensitive Rainbow (RS-Rainbow) is an end-to-end trainable network based on the original Rainbow, a powerful deep Q-network agent. Our proposed agent, named region-sensitive Rainbow (RS-Rainbow), is an end-to-end trainable network based on the original Rainbow, a powerful deep Q-network agent.
• Score: 106.21468537372995
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep reinforcement learning (DeepRL) agents surpass human-level performance in many tasks. However, the direct mapping from states to actions makes it hard to interpret the rationale behind the decision-making of the agents. In contrast to previous a-posteriori methods for visualizing DeepRL policies, in this work, we propose to equip the DeepRL model with an innate visualization ability. Our proposed agent, named region-sensitive Rainbow (RS-Rainbow), is an end-to-end trainable network based on the original Rainbow, a powerful deep Q-network agent. It learns important regions in the input domain via an attention module. At inference time, after each forward pass, we can visualize regions that are most important to decision-making by backpropagating gradients from the attention module to the input frames. The incorporation of our proposed module not only improves model interpretability, but leads to performance improvement. Extensive experiments on games from the Atari 2600 suite demonstrate the effectiveness of RS-Rainbow.

Related papers

• An Examination of Offline-Trained Encoders in Vision-Based Deep Reinforcement Learning for Autonomous Driving [0.0]
  Research investigates the challenges Deep Reinforcement Learning (DRL) faces in Partially Observable Markov Decision Processes (POMDP) Our research adopts an offline-trained encoder to leverage large video datasets through self-supervised learning to learn generalizable representations. We show that the features learned by watching BDD100K driving videos can be directly transferred to achieve lane following and collision avoidance in CARLA simulator.
  arXiv  Detail & Related papers  (2024-09-02T14:16:23Z)
• SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies [13.26174103650211]
  A lack of explainability of learned policies impedes its uptake in safety-critical applications, such as automated driving systems. Counterfactual (CF) explanations have recently gained prominence for their ability to interpret black-box Deep Learning (DL) models. We propose using a saliency map to identify the most influential input pixels across the sequence of past observed states by the agent. We evaluate the effectiveness of our framework in diverse domains, including ADS, Atari Pong, Pacman and space-invaders games.
  arXiv  Detail & Related papers  (2024-04-28T21:47:34Z)
• Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning [69.19840497497503]
  It is argued that the commonly used action matching principle is more like an explanation of deep neural networks (DNNs) than the interpretation of RL agents. We propose to consider rewards, the essential objective of RL agents, as the essential objective of interpreting RL agents. We verify and evaluate our method on the Atari 2600 games as well as Duckietown, a challenging self-driving car simulator environment.
  arXiv  Detail & Related papers  (2023-09-04T09:09:54Z)
• 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)
• Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning [9.072416458330268]
  In this work, we demonstrate that the learned representation of the $Q$-network and its target $Q$-network should, in theory, satisfy a favorable distinguishable representation property. We propose Policy Evaluation with Easy Regularization on Representation (PEER), which aims to maintain the distinguishable representation property via explicit regularization on internal representations. PEER achieves state-of-the-art performance on all 4 environments on PyBullet, 9 out of 12 tasks on DMControl, and 19 out of 26 games on Atari.
  arXiv  Detail & Related papers  (2022-05-29T02:29:32Z)
• Retrieval-Augmented Reinforcement Learning [63.32076191982944]
  We train a network to map a dataset of past experiences to optimal behavior. The retrieval process is trained to retrieve information from the dataset that may be useful in the current context. We show that retrieval-augmented R2D2 learns significantly faster than the baseline R2D2 agent and achieves higher scores.
  arXiv  Detail & Related papers  (2022-02-17T02:44:05Z)
• Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model [78.69367679848632]
  We describe a lightweight and effective method to derive explanations for deep RL agents. Our method relies on a transformation of the pixel-based input of the RL agent to an interpretable, percept-like input representation. We then train a surrogate model, which is itself interpretable, to replicate the behavior of the target, deep RL agent.
  arXiv  Detail & Related papers  (2021-10-07T05:01:44Z)
• Are Gradient-based Saliency Maps Useful in Deep Reinforcement Learning? [4.254099382808598]
  Deep Reinforcement Learning (DRL) connects the classic Reinforcement Learning algorithms with Deep Neural Networks. A problem in DRL is that CNNs are black-boxes and it is hard to understand the decision-making process of agents. This work brings some of the best-known visualization methods from the field of image classification to the area of Deep Reinforcement Learning.
  arXiv  Detail & Related papers  (2020-12-02T15:38:36Z)
• Context-Aware RCNN: A Baseline for Action Detection in Videos [66.16989365280938]
  We first empirically find the recognition accuracy is highly correlated with the bounding box size of an actor. We revisit RCNN for actor-centric action recognition via cropping and resizing image patches around actors. We found that expanding actor bounding boxes slightly and fusing the context features can further boost the performance.
  arXiv  Detail & Related papers  (2020-07-20T03:11:48Z)

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.