diff --git a/config.yaml b/config.yaml index 0f718ad3..6a2af8b6 100755 --- a/config.yaml +++ b/config.yaml @@ -62,9 +62,9 @@ pokemon_red: package: pokemon_red train: total_timesteps: 800_000_000 - num_envs: 512 # 256 - envs_per_worker: 4 - envs_per_batch: 120 # 48 # must be divisible by envs_per_worker + num_envs: 128 # 256 + envs_per_worker: 1 # 4 + envs_per_batch: 64 # 120 # 48 # must be divisible by envs_per_worker update_epochs: 3 # 10 # 3 gamma: 0.998 batch_size: 65536 # 65536 # 32768 @@ -84,7 +84,7 @@ pokemon_red: fast_video: True explore_weight: 1.5 use_screen_explore: False - sim_frame_dist: 2000000.0 # 2000000.0 + sim_frame_dist: 3000000.0 # 2000000.0 # 2000000.0 reward_scale: 4 extra_buttons: False noop_button: True @@ -98,7 +98,7 @@ pokemon_red: enable_item_purchaser: True # True auto_skip_anim: True auto_skip_anim_frames: 8 - total_envs: 512 # 48 # Updated to match num_cpu + total_envs: 128 # 512 # 48 # Updated to match num_cpu gb_path: PokemonRed.gb debug: False level_manager_eval_mode: False diff --git a/pufferlib/environments/pokemon_red/environment.py b/pufferlib/environments/pokemon_red/environment.py index 6051a5bc..a920bfd7 100755 --- a/pufferlib/environments/pokemon_red/environment.py +++ b/pufferlib/environments/pokemon_red/environment.py @@ -24,7 +24,7 @@ def env_creator(name="pokemon_red"): def make(name, **kwargs,): """Pokemon Red""" env = Environment(kwargs) - env = StreamWrapper(env, stream_metadata={"user": "PUFFERBOX5|BET|\n=BOEY=\n"}) + env = StreamWrapper(env, stream_metadata={"user": "PUFFERBOX5 |BET|\n=BOEY=\n"}) # Looks like the following will optionally create the object for you # Or use the one you pass it. I'll just construct it here. return pufferlib.emulation.GymnasiumPufferEnv( diff --git a/run.sh b/run.sh index c8df9819..e9120a93 100755 --- a/run.sh +++ b/run.sh @@ -1,2 +1,2 @@ #!/bin/bash -python demo.py --backend clean_pufferl --config pokemon_red --no-render --vectorization multiprocessing --mode train --track # --exp-name test4 # --wandb-entity xinpw8 \ No newline at end of file +python demo.py --backend clean_pufferl --config pokemon_red --no-render --vectorization multiprocessing --mode train --track --wandb-entity xinpw8 --exp-name boey_test_pufferbox5 \ No newline at end of file