LizGoban 0.8.0-pre5

• Upgrade KataGo to 1.15.1.
• Separate the model files from *.exe for larger models including a model for human-like style.
• Add "human-style" features.
  • Compare the policies between 5kyu and 1dan, for example.
  • Play human-like moves for the specified rank.
• Warn overlooked high-policy best moves by squares on stones.
• Avoid too stupid moves in persona strategy.
• Add random pair match.
• Deleted boards are also listed in "Open recent" menu.
• Deprecate the display of preferred moves by "AIs for handicap games".
• Deprecate homemade "aggressiveness" features and rely on the native KataGo features.

Incompatibilities:

• Change the autosave format.
• Upgrade libraries (Electron 31, etc.). So you may need to do "npm install" again if you use LizGoban from the command line.

Human-style features

Choose "Human-like Analysis" or "Human-like Play" from "Preset" menu and refer to "KataGo" section in "Help" menu for details.

Thanks to dfannius; this analysis feature is a variation of his "policy heatmap".

To use it on 64bit Windows immediately

Just download the all-in-one package (LizGoban-*_win_*.zip), unzip it, and double-click LizGoban *.exe. You do not need installation, configuration, additional downloads, and so on. Its file size is due to the built-in engine:

• KataGo 1.15.1 (eigenavx2, opencl) + 18 block network (kata1-b18c384nbt-s9996) + human-trained network (b18c384nbt-humanv0.bin.gz)

You can switch KataGo versions (CPU and GPU) by [Preset] menu in LizGoban. The first run of the GPU version may take a long time (1 hour on a low-spec machine, for example) for its initial tuning. You can also choose "Human-like Analysis" or "Human-like Play" from [Preset] menu. Refer to "KataGo" section in [Help] menu for details.

To customize it on 64bit Windows

If you want to use another network (aka. model, weights), you can simply click the Engine menu and select "Load network weights". Additionally, you can modify the config.json file for more flexible configuration. See README for details.

To use it on other platforms (Mac, Linux, ...)

Download the source code and see README.md.

LizGoban 0.8.0-pre4

• Upgrade KataGo to 1.14.0.
• Add sound feature. (You need to prepare and set sound files by yourself.)
• Replace SOPPO indicator with playing styles indicator.
• Add playing styles indicator to ownership distribution chart.
• Change playing style of persona strategy. This is still being tested and might change in the future.
• Avoid unnatural tenuki in match vs. weakened AI.
• Add "Open recent" to File menu.
• Detect encoding of SGF files etc.
• Support TamaGo. (You need a patch currently on 2023-12-28.)

Minor changes:

• Add "board_size" and "wait_for_startup" to preset in config.json.
• Make Ctrl-, key toggle preferences window.
• Enable app.quit() in REPL for external control.
• Add "default preset" to "Engine is down" dialog for SSH disconnection.
• Use entropy as the ambiguity measure.
• Fix bugs.

Incompatibilities:

• Upgrade libraries (Electron 28, etc.). So you may need to do "npm install" again if you use LizGoban from the command line.

Acknowledgement:

• Thanks to qcgm1978 for the contributions and suggestions.

LizGoban 0.8.0-pre3

• Fix bugs. (wrong ruleset, reset of visit count)

LizGoban 0.8.0-pre2

• Upgrade KataGo to 1.13.0.
• Provide simpler methods to replace the built-in engine / network. Details are available in the notes below.
• Add leadings chart.
• Delete move numbers from tsumego frame to prevent potential confusion for KataGo.

Incompatibilities:

• Upgrade libraries (Electron 25, etc.). So you may need to do "npm install" again if you use LizGoban from the command line.

To use it on 64bit Windows immediately

Just download the all-in-one package (LizGoban-*_win_*.zip), unzip it, and double-click LizGoban *.exe. You do not need installation, configuration, additional downloads, and so on. Its file size is due to the built-in engine:

• KataGo 1.13.0 (eigen, eigenavx2, opencl) + 15 block network (g170e-b15c192-s1672 from KataGo 1.4.5)

You can switch KataGo versions (CPU, modern CPU, GPU) by [Preset] menu in LizGoban. The first run of the GPU version may take a long time (1 hour on a low-spec machine, for example) for its initial tuning.

To customize it on 64bit Windows

If you want to replace built-in network (aka. model, weights)...

1. Download and unzip the same all-in-one package as above.
2. Copy sample/custom_model/config.json to the same folder as LizGoban *.exe.
3. Download your favorite network, rename it to katanetwork.gz, and place it in the same folder.

If you want to replace built-in katago...

1. Download and unzip the same all-in-one package as above.
2. Copy sample/custom_katago/config.json to the same folder as LizGoban *.exe.
3. Place your favorite katago and its network in the same folder. They must be renamed to katago.exe and katanetwork.gz, respectively.

If you just want to modify the configurations of built-in katago...

1. Download and unzip the same all-in-one package as above.
2. Copy sample/built_in/config.json to the same folder as LizGoban *.exe.
3. Edit it as you like. See README for its format.

To use it on other platforms (Mac, Linux, ...) or Windows with more flexible configuration

Download the source code and see README.md.

LizGoban 0.8.0-pre1

• Upgrade KataGo to 1.12.4.
• Blur ownership display. (Borrow the idea from katrain#555.)
• Replace zone indicator with SOPPO indicator for successive misses of the best move.
• Add ownership distribution chart at the bottom left. (Press "x" key to enlarge it.)
• Add thin red background for "hot" periods in winrate graph.
• Add "ambiguity of areas" (faint gray line) and "settled territories" (faint green/pink dots) to score graph.
• Highlight settled areas by "v" key.
• Make long press of cursor keys smoother.
• Fix minor bugs.

Incompatibilities:

• Upgrade libraries (Electron 24, etc.). So you may need to do "npm install" again if you use LizGoban from the command line.

To use it on 64bit Windows immediately

Just download the all-in-one package (LizGoban-*_win_*.zip), unzip it, and double-click LizGoban *.exe. You do not need installation, configuration, additional downloads, and so on. Its file size is due to the built-in engine:

• KataGo 1.12.4 (eigen, eigenavx2, opencl) + 15 block network (g170e-b15c192-s1672 from KataGo 1.4.5)

You can switch KataGo versions (CPU, modern CPU, GPU) by [Preset] menu in LizGoban. The first run of the GPU version may take a long time (1 hour on a low-spec machine, for example) for its initial tuning.

To customize it on 64bit Windows

If you want to replace built-in network (aka. model, weights)...

1. Download and unzip the same all-in-one package as above.
2. Copy sample/custom_model/config.json to the same folder as LizGoban *.exe.
3. Download your favorite network, rename it to katanetwork.gz, and place it in the same folder.

If you want to replace built-in katago...

1. Download and unzip the same all-in-one package as above.
2. Copy sample/custom_katago/config.json to the same folder as LizGoban *.exe.
3. Place your favorite katago and its network in the same folder. They must be renamed to katago.exe and katanetwork.gz, respectively.

If you just want to modify the configurations of built-in katago...

1. Download and unzip the same all-in-one package as above.
2. Copy sample/built_in/config.json to the same folder as LizGoban *.exe.
3. Edit it as you like. See README for its format.

To use it on other platforms (Mac, Linux, ...) or Windows with more flexible configuration

Download the source code and see README.md.

LizGoban 0.7.0

• Upgrade KataGo to 1.11.0.
• Add items to "AI strategy". (See "Help" menu for details)
  • "persona": Randomly generate various playing styles for weak bots to avoid boredom. It also has "automatic adjustment of strength" and "virtual character system". You can input any name to generate a bot with the parameters based on its name. For example, "jowa" prefers to capture stones, "alex" likes positional plays, etc. Try various names to find your favorite opponents.
  • "pass": AI plays "pass" if there is room.
  • "swap n": AI uses either of two engines at random.
• Support the new feature "ownershipStdev" in KataGo 1.10.0 (red backgrounds in the subboard), that looks like a heatmap of "KataGo's eye tracking".
• Support "movesOwnership" in KataGo 1.11.0.
• Show the preferred moves by "AIs for handicap games" as the stronger/weaker side. (small blue up/down triangles on the board, sharpness of the triangles in the winrate bar)
• Add automatic adjustment for [SGF from Image].
• Add "Auto overview" into Tool menu so that one can turn it off.
• Add "Preferences" into Edit menu for convenience.
• Slightly improve bogus territory counts.
• Slightly improve ladder continuation.
• Use change of ownership in addition to ownership itself for facial stones.
• Guess the rule from komi if RU (rule) property is missing in SGF.
• Officially support tsumego frame and ladder continuation.
• Fix SSL issue on Let's Encrypt. (ref ref)
• The keyboard shortcuts "0" to "9" are deleted for match vs. AI with obsolete strategies.

Incompatibilities:

• Upgrade libraries (Electron 18, etc.). So you may need to do "npm install" again.

To use it on 64bit Windows immediately

Just download the all-in-one package (LizGoban-*_win_*.zip), unzip it, and double-click LizGoban *.exe. You do not need installation, configuration, additional downloads, and so on. Its file size is due to the built-in engine:

• KataGo 1.11.0 (eigen, eigenavx2, opencl) + 15 block network (g170e-b15c192-s1672 from KataGo 1.4.5)

You can switch KataGo versions (CPU, modern CPU, GPU) by [Preset] menu in LizGoban. The first run of the GPU version may take a long time (1 hour on a low-spec machine, for example) for its initial tuning.

To customize it on 64bit Windows

If you want to use other engines, network files, options, ...

1. Prepare engines (Leela Zero and/or KataGo) and their network files (aka. weights, models) by yourself, if necessary.
2. Download and unzip the same all-in-one package as above.
3. Copy sample/config.json to the same folder as LizGoban *.exe and edit it. See README for its format.

To use it on other platforms (Mac, Linux, ...) or Windows with more flexible configuration

Download the source code and see README.md.

LizGoban 0.7.0-pre4

• Tune the behavior of "AI persona".
• Officially support movesOwnership in KataGo 1.11.0.
• Add auto-adjustment for [SGF from Image].
• Add items to the pull down menu of AI strategy and delete the corresponding keyboard shortcuts "1" to "9" instead.
  • "pass": AI plays "pass" if there is room.
  • "swap n": AI swaps engines for black and white randomly with probability 10n%. (You need to set engines with different configurations, e.g. LZ38 and LZ157, for black and white beforehand from "Engine" menu or "Preset" menu.)
• Use change of ownership in addition to ownership itself for facial stones.
• (Remove 3n opening method for handicap games.)

If you are willing to help developments, please try new weak bots for matches vs. AI (work in progress). This is a step toward ideal bots that have a wide variety of playing styles and auto-adjusted strength without unnaturally stupid moves.

1. Click "File > Match vs. AI".
2. Click the pull down menu beside "vs." and select "persona".
3. Click the board to play a game.

You can play against bots with randomly generated characteristics from "..." button. You can also adjust "sanity" slider anytime, or check "auto" for auto-adjusting.

In addition, there is a new system of virtual opponent characters. When you input any name from "..." button, LizGoban generates a bot with the parameters based on its name. For example, "jowa" prefers to capture stones, "alex" likes positional plays, etc. Try various names to find your favorite opponents. Note that unreasonable strategies are still tough if you set high "sanity" because the moves are selected only in major suggestions by AI.

LizGoban 0.7.0-pre3

• Upgrade KataGo to 1.11.0.
• Show the preferred moves by "AIs for handicap games" as the stronger/weaker side. (small blue up/down triangles on the board, sharpness of the triangles in the winrate bar)
• Add "Preferences" into Edit menu for convenience.
• Slightly improve ladder continuation.
• (Bonus) 3n opening method for handicap games in Tool > Experimental. This is just a temporary trial and will be removed in the next release. See #75.

If you are willing to help developments, please try new weak bots for matches vs. AI (work in progress). This is a step toward ideal bots that have a wide variety of playing styles and auto-adjusted strength without unnaturally stupid moves.

1. Enable "Edit > Preferences > Ownerships per move".
2. Click "File > Match vs. AI".
3. Click the pull down menu beside "vs." and select "(persona)" at the bottom.
4. Click the board to play a game.

You can play against bots with randomly generated characteristics from "..." button. You can also adjust "sanity" slider anytime, or check "auto" for auto-adjusting.

In addition, there is a new system of virtual opponent characters. When you input any name from "..." button, LizGoban generates a bot with the parameters based on its name. For example, "jowa" prefers to capture stones, "alex" likes positional plays, etc. Try various names to find your favorite opponents. Note that unreasonable strategies are still tough if you set high "sanity" because the moves are selected only in major suggestions by AI.

Incompatibilities:

• Upgrade libraries (Electron 17, etc.). So you may need to do "npm install" again.

LizGoban 0.7.0-pre2

• Upgrade KataGo to 1.10.0.
• Support the new feature "ownershipStdev" in KataGo 1.10.0 (red backgrounds in the subboard), that looks like a heatmap of "KataGo's eye tracking".

LizGoban 0.7.0-pre1

• Add "Auto overview" into Tool menu so that one can turn it off.
• Slightly improve bogus territory counts.
• Guess the rule from komi if RU (rule) property is missing in SGF.
• Fix SSL issue on Let's Encrypt. (ref ref)

Incompatibilities:

• Upgrade libraries (Electron 15, etc.). So you may need to do "npm install" again.