From 0e8a4af7407704d9fb9f6d3ada88169f0062019e Mon Sep 17 00:00:00 2001 From: Steffen Illium Date: Tue, 11 Jan 2022 14:27:08 +0100 Subject: [PATCH] Debugging --- environments/factory/factory_dirt.py | 4 ++-- environments/helpers.py | 10 +++++----- studies/single_run_with_export.py | 8 ++++---- 3 files changed, 11 insertions(+), 11 deletions(-) diff --git a/environments/factory/factory_dirt.py b/environments/factory/factory_dirt.py index 077b44e..8ab6c69 100644 --- a/environments/factory/factory_dirt.py +++ b/environments/factory/factory_dirt.py @@ -28,9 +28,9 @@ class Actions(BaseActions): class Rewards(BaseRewards): - CLEAN_UP_VALID = 1 + CLEAN_UP_VALID = 0.5 CLEAN_UP_FAIL = -0.1 - CLEAN_UP_LAST_PIECE = 4 + CLEAN_UP_LAST_PIECE = 4.5 class DirtProperties(NamedTuple): diff --git a/environments/helpers.py b/environments/helpers.py index d90849d..b340771 100644 --- a/environments/helpers.py +++ b/environments/helpers.py @@ -79,11 +79,11 @@ class EnvActions: class Rewards: MOVEMENTS_VALID = -0.01 - MOVEMENTS_FAIL = -0.1 - NOOP = -0.01 - USE_DOOR_VALID = -0.01 - USE_DOOR_FAIL = -0.1 - COLLISION = -0.5 + MOVEMENTS_FAIL = -0.10 + NOOP = -0.01 + USE_DOOR_VALID = -0.00 + USE_DOOR_FAIL = -0.10 + COLLISION = -0.5 m = EnvActions diff --git a/studies/single_run_with_export.py b/studies/single_run_with_export.py index 5d9ff88..be61fd9 100644 --- a/studies/single_run_with_export.py +++ b/studies/single_run_with_export.py @@ -113,10 +113,10 @@ if __name__ == '__main__': # What to do: train = True individual_run = True - combined_run = True + combined_run = False multi_env = False - train_steps = 2e5 + train_steps = 2e6 frames_to_stack = 3 # Define a global studi save path @@ -155,8 +155,8 @@ if __name__ == '__main__': env_map = {} env_map.update({'dirt': (DirtFactory, dict(dirt_prop=dirt_props, **factory_kwargs.copy()))}) - # env_map.update({'item': (ItemFactory, dict(item_prop=item_props, - # **factory_kwargs.copy()))}) + env_map.update({'item': (ItemFactory, dict(item_prop=item_props, + **factory_kwargs.copy()))}) # env_map.update({'dest': (DestFactory, dict(dest_prop=dest_props, # **factory_kwargs.copy()))}) env_map.update({'combined': (DirtDestItemFactory, dict(dest_prop=dest_props,