From 96847f097e4c2fd0148f53b610ecc2bdb401fd52 Mon Sep 17 00:00:00 2001 From: Gautier Hamon <76616547+Reytuag@users.noreply.github.com> Date: Tue, 21 May 2024 18:58:56 +0200 Subject: [PATCH] Add PPO-GTrXL to scoreboard (#23) --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index b517070..13c3502 100644 --- a/README.md +++ b/README.md @@ -115,6 +115,7 @@ We report reward as a % of the maximum (226). ## Craftax-1B | Algorithm | Reward (% max) | Code | Paper | |:----------|---------------:|:-----------------------------------------------------------------------------------------------:|:---------------------------------------:| +| PPO-GTrXL | 18.3 | [TransformerXL_PPO_JAX](https://github.com/Reytuag/transformerXL_PPO_JAX) | [PPO](https://arxiv.org/abs/1707.06347), [GTrXL](https://arxiv.org/abs/1910.06764)| | PPO-RNN | 15.3 | [Craftax_Baselines](https://github.com/MichaelTMatthews/Craftax_Baselines/blob/main/ppo_rnn.py) | [PPO](https://arxiv.org/abs/1707.06347) | | RND | 12.0 | [Craftax_Baselines](https://github.com/MichaelTMatthews/Craftax_Baselines/blob/main/ppo_rnd.py) | [RND](https://arxiv.org/abs/1810.12894) | | PPO | 11.9 | [Craftax_Baselines](https://github.com/MichaelTMatthews/Craftax_Baselines/blob/main/ppo.py) | [PPO](https://arxiv.org/abs/1707.06347) | @@ -156,4 +157,4 @@ If you use Craftax in your work please cite it as follows: journal={arXiv preprint}, year={2024}, } -``` \ No newline at end of file +```