From bf2d6b19431f6e4150e5afcb9be7c935ded0e1a6 Mon Sep 17 00:00:00 2001 From: Vincent Micheli Date: Mon, 3 Oct 2022 17:41:55 +0200 Subject: [PATCH] Update README.md --- README.md | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/README.md b/README.md index 06bcf80..05ec809 100644 --- a/README.md +++ b/README.md @@ -121,13 +121,7 @@ Pretrained models are available in `pretrained_models/`. - To start a training run from one of these checkpoints, in the section `initialization` of `config/trainer.yaml`, set `path_to_checkpoint` to the corresponding path, and `load_tokenizer`, `load_world_model`, and `load_actor_critic` to `True`. -- To visualize one of these checkpoints, run the following commands: - ```bash - mkdir checkpoints - cp pretrained_models/Breakout.pt checkpoints/last.pt - ./scripts/play.sh - ``` - with optionally the flags described above for `play.sh`. +- To visualize one of these checkpoints, set `train.id` to the corresponding game in `config/env/default.yaml`, create a `checkpoints` directory and copy the checkpoint to `checkpoints/last.pt`. You can then visualize the agent with `./scripts/play.sh` as described above. ## Credits