2021
DOI: 10.48550/arxiv.2105.14039
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Towards mental time travel: a hierarchical memory for reinforcement learning agents

Abstract: Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to recall the details of a single timestep that is followed by distractor tasks. To address these limitations, we propose a Hierarchical Transformer Memory (HTM), which helps agents to remember the past in detail. HTM stores memories by dividing the past into chunks, and recalls by… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 31 publications
0
2
0
Order By: Relevance
“…Whilst the majority of deep RL algorithms use experience to update the policy and/or value functions offline, some RL methods have taken direct inspiration from episodic memory to create policies that are directly conditioned on past experiences (Blundell et al, 2016;Pritzel et al, 2017). Sufficiently large buffers of experiences, which can be queried as needed during the learning of a novel task, provide powerful retrospective learning (Lampinen, Chan, Banino, & Hill, 2021), but limited future-oriented imagination.…”
Section: Experience Generation In Artificial Agentsmentioning
confidence: 99%
See 1 more Smart Citation
“…Whilst the majority of deep RL algorithms use experience to update the policy and/or value functions offline, some RL methods have taken direct inspiration from episodic memory to create policies that are directly conditioned on past experiences (Blundell et al, 2016;Pritzel et al, 2017). Sufficiently large buffers of experiences, which can be queried as needed during the learning of a novel task, provide powerful retrospective learning (Lampinen, Chan, Banino, & Hill, 2021), but limited future-oriented imagination.…”
Section: Experience Generation In Artificial Agentsmentioning
confidence: 99%
“…Initial attempts to imitate hippocampal episodic control (Lengyel & Dayan, 2007) in AI agents used non-parametric (Blundell et al, 2016) and semi-parametric (Pritzel et al, 2017) memories (which store state information from every timestep), enabling rapid learning when compared to standard deep RL algorithms. Scaling such memory is an open challenge, with possible solutions including more sophisticated storage/forgetting mechanisms, compression (Agostinelli, Arulkumaran, Sarrico, Richemond, & Bharath, 2019), and hierarchy (Lampinen et al, 2021). Still, these algorithms only correspond to replay, while combining episodic memories with generative models could lead to further abilities, such as planning to find outcomes that are of specific relevance to the agent (Zakharov et al, 2021).…”
Section: Implementing Access Consciousness In Artificial Agentsmentioning
confidence: 99%