Behaviour Suite for Reinforcement Learning
This paper introduces the Behaviour Suite for Reinforcement Learning, or bsuite for short. bsuite is a collection of carefully-designed experiments that investigate core capabilities of reinforcement learning (RL) agents with two objectives. First, to collect clear, informative and scalable problems that capture key issues in the design of general and efficient learning algorithms. Second, to study agent behaviour through their performance on these shared benchmarks. To complement this effort, we open source github.com/deepmind/bsuite, which automates evaluation and analysis of any agent on bsuite. This library facilitates reproducible and accessible research on the core issues in RL, and ultimately the design of superior learning algorithms. Our code is Python, and easy to use within existing projects. We include examples with OpenAI Baselines, Dopamine as well as new reference implementations. Going forward, we hope to incorporate more excellent experiments from the research community, and commit to a periodic review of bsuite from a committee of prominent researchers.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Ian Osband (edit)
Yotam Doron (add twitter)
Matteo Hessel (edit)
John Aslanides (edit)
Eren Sezener (edit)
Andre Saraiva (add twitter)
Katrina McKinney (add twitter)
Tor Lattimore (add twitter)
Csaba Szepezvari (add twitter)
Satinder Singh (edit)
Benjamin Van Roy (add twitter)
Richard Sutton (add twitter)
David Silver (edit)
Hado Van Hasselt (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
Stargazers:
209
Forks:
13
Open Issues:
0
Network:
13
Subscribers:
16
Language:
Python
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
08/12/19 06:08PM
7,989
2,587
Tweets
hasansaikatt: RT @arxiv_org: Behaviour Suite for Reinforcement Learning. https://t.co/SmpvFXewuJ https://t.co/6vDoKBDzUy
Rosenchild: RT @arxiv_org: Behaviour Suite for Reinforcement Learning. https://t.co/SmpvFXewuJ https://t.co/6vDoKBDzUy
MasterScrat: @MelMitchell1 @GaryMarcus The intro from DeepMind's latest paper is highly relevant (https://t.co/JN2tvsdAi8) - can't be a coincidence, published a few days after their losses were announced https://t.co/V0NzRINgYW
panchovie: RT @mooopan: とりあえず著者の顔ぶれがすごい https://t.co/q4hn6i7Aiw
DataScientistFr: We are excited to release Behaviour Suite for Reinforcement Learning, or ‘bsuite’ – a collection of carefully-designed experiments that investigate core capabilities of RL agents GitHub: https://t.co/Ud44RozkyC Paper: https://t.co/poeYoe9LnS… - https://t.co/KohGu64tGz #da…
moe_moe_moegi: RT @mooopan: とりあえず著者の顔ぶれがすごい https://t.co/q4hn6i7Aiw
AnalyticsFr: We are excited to release Behaviour Suite for Reinforcement Learning, or ‘bsuite’ – a collection of carefully-designed experiments that investigate core capabilities of RL agents GitHub: https://t.co/w6afyhHGY6 Paper: https://t.co/e9x7ZhIprr… - https://t.co/7wKUdfEXs1 #An…
fujisawaIFE: RT @mooopan: とりあえず著者の顔ぶれがすごい https://t.co/q4hn6i7Aiw
KazuSamejima: RT @mooopan: とりあえず著者の顔ぶれがすごい https://t.co/q4hn6i7Aiw
mooopan: とりあえず著者の顔ぶれがすごい https://t.co/q4hn6i7Aiw
arxiv_cs_LG: Behaviour Suite for Reinforcement Learning. Osband, Doron, Hessel, Aslanides, Sezener, Saraiva, McKinney, Lattimore, Szepezvari, Singh, Roy, Sutton, Silver, and Hasselt https://t.co/eIU2yIyvdw
fullNam35087976: RT @arxiv_org: Behaviour Suite for Reinforcement Learning. https://t.co/SmpvFXewuJ https://t.co/6vDoKBDzUy
Rosenchild: RT @arxiv_org: Behaviour Suite for Reinforcement Learning. https://t.co/SmpvFXewuJ https://t.co/6vDoKBDzUy
bottom100x100: RT @arxiv_org: Behaviour Suite for Reinforcement Learning. https://t.co/SmpvFXewuJ https://t.co/6vDoKBDzUy
mr_ubik: RT @arxiv_org: Behaviour Suite for Reinforcement Learning. https://t.co/SmpvFXewuJ https://t.co/6vDoKBDzUy
arxiv_org: Behaviour Suite for Reinforcement Learning. https://t.co/SmpvFXewuJ https://t.co/6vDoKBDzUy
LanternInst: Behaviour Suite for Reinforcement Learning #ArtificialIntelligence #Behaviour #ai via https://t.co/jnJxWgplgl https://t.co/uaepVMpx48
arxivml: "Behaviour Suite for Reinforcement Learning", Ian Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener,… https://t.co/Wgh3wpcvYH
MASSIMOFERRO19: RT @StatsPapers: Behaviour Suite for Reinforcement Learning. https://t.co/ySa2FwPrlH
fullNam35087976: RT @StatsPapers: Behaviour Suite for Reinforcement Learning. https://t.co/ySa2FwPrlH
StatsPapers: Behaviour Suite for Reinforcement Learning. https://t.co/ySa2FwPrlH
amruthasuri: Behaviour Suite for Reinforcement Learning #ArtificialIntelligence #Behaviour #ai via https://t.co/gydENhzRSg https://t.co/JKwms1N4g9
jerinsantosh: Behaviour Suite for Reinforcement Learning #ArtificialIntelligence #Behaviour #ai via https://t.co/ZGDPhfa1ir https://t.co/lUZFab1Kts
Images
Related