open-spaced-repetition/fsrs-optimizer

Issues

• Enforce S0(Again) < S0(Hard) < S0(Good) < S0(Easy)

  #133 opened 8 days ago by Expertium
  3

• Change l1 = np.abs(stability - init_s0) / 16

  #144 opened 12 days ago by Expertium
  2

• FSRS-5 优化器，优化参数时发生报错：“error Columns not found: 1, 2, 3, 4”

  #134 opened 2 months ago by hihaojie
  5

• In the stability charts, change RMSE to MAPE

  #130 opened 3 months ago by Expertium
  0

• `optimizer.create_time_series` raises Exception

  #125 opened 3 months ago by YukiNagat0
  2

• try ruff in ci?

  #119 opened 4 months ago by asukaminato0721
  2

• Q: Effect of review_duration column on weights

  #118 opened 4 months ago by joshdavham
  1

• [Feature request] Further improving the estimation of reviews times for calculating minimum recommended retention

  #116 opened 5 months ago by Expertium
  13

• A better outlier filter for "Compute minimum recommended retention"

  #112 opened 5 months ago by Expertium
  2

• Use the median instead of the mean for recall costs and learn cost

  #107 opened 6 months ago by Expertium
  8

• [Feature Request] Add another condition to the outlier filter

  #83 opened 8 months ago by Expertium
  4

• [Feature Request] Investigate how robust are parameters and RMSE

  #64 opened 10 months ago by Expertium
  18

• Optimized w[3] too low

  #69 opened 10 months ago by user1823
  12

• See if this code could be used to speed up finding optimal retention

  #60 opened a year ago by Expertium
  16

• [Feature request] Improve post-lapse stability analysis

  #55 opened a year ago by Expertium
  13

• [Feature Request] Loosen the clampings for w[9]

  #30 opened a year ago by Expertium
  5

• Use results from benchmark experiment as initial values of S0

  #23 opened a year ago by user1823
  12

• [Question] Explain how the optimizer calculates retention that minimizes review times

  #38 opened a year ago by Expertium
  12

• [Bug] Can't use absolute path as arg

  #43 opened a year ago by tkngaejcpi
  1

• [BUG] 'Optimizer' object has no attribute 'w'

  #45 opened a year ago by HominidaeBlaze
  1

• [Feature Request] make the simulator more precise by using different values of recall_cost for Hard, Good and Easy

  #41 opened a year ago by Expertium
  0

• Training data is inadequate.

  #36 opened a year ago by mdzz2048
  5

• index 1 is out of bounds for axis 0 with size 1 [BUG]

  #32 opened a year ago by cocowash
  1

• [BUG] Loosen the clamping for w[10] and w[8]

  #28 opened a year ago by L-M-Sherlock
  5

• Optimizer filtering out data which is not outlier

  #16 opened a year ago by user1823
  58

• Command Line typo on usage section fsrs-optimizer doesn't exist [BUG]

  #24 opened a year ago by cocowash
  1

• [BUG] file not found when running local optimizer for multiple decks

  #21 opened a year ago by ruilya
  2

• [Feature request] A way to extrapolate values of S0 without curve_fit

  #19 opened a year ago by Expertium
  8

• how to input data from obsidian-spaced-repetition-recall, ob-revlog.csv, into optimizer

  #13 opened a year ago by dryezl
  26

• [BUG] Initial stability for "Good" will be larger than for "Easy" if "Good" has more datapoint

  #11 opened a year ago by L-M-Sherlock
  24

• [BUG] Exaggerated ranges after optimizing

  #5 opened a year ago by JeffersonCorreia32a
  61

• [BUG] Optimizer error: "stack expects each tensor to be equal size, but got [...] at entry 0 and [...] at entry 1"

  #9 opened a year ago by Zaldroc8
  2

• [Feature Request] write plot files to local directory

  #3 opened a year ago by L-M-Sherlock
  0