Skip to content

Updated to work with v26 of OpenAI Gym #31

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
BlueHephaestus wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Updated to work with v26 of OpenAI Gym #31

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2184c63
Updated to work with v26 of OpenAI Gym
BlueHephaestus Jan 7, 2024
40d018e
rollback local change
BlueHephaestus Jan 7, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 9 additions & 6 deletions pureples/shared/gym_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ def eval_fitness(genomes, config):
fitnesses = []

for _ in range(trials):
ob = env.reset()
ob = env.reset()[0]
net.reset()

total_reward = 0
Expand All @@ -45,7 +45,8 @@ def eval_fitness(genomes, config):
o = net.activate(ob)

action = np.argmax(o)
ob, reward, done, _ = env.step(action)
ob, reward, terminated, truncated, _ = env.step(action)
done = terminated or truncated
total_reward += reward
if done:
break
Expand Down Expand Up @@ -91,7 +92,7 @@ def eval_fitness(genomes, config):
fitnesses = []

for _ in range(trials):
ob = env.reset()
ob = env.reset()[0]
net.reset()

total_reward = 0
Expand All @@ -100,7 +101,8 @@ def eval_fitness(genomes, config):
for _ in range(activations):
o = net.activate(ob)
action = np.argmax(o)
ob, reward, done, _ = env.step(action)
ob, reward, terminated, truncated, _ = env.step(action)
done = terminated or truncated
total_reward += reward
if done:
break
Expand Down Expand Up @@ -143,14 +145,15 @@ def eval_fitness(genomes, config):
fitnesses = []

for _ in range(trials):
ob = env.reset()
ob = env.reset()[0]

total_reward = 0

for _ in range(max_steps):
o = net.activate(ob)
action = np.argmax(o)
ob, reward, done, _ = env.step(action)
ob, reward, terminated, truncated, _ = env.step(action)
done = terminated or truncated
total_reward += reward
if done:
break
Expand Down
2 changes: 1 addition & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

setup(
name='pureples',
version='0.0',
version='0.1',
author='adrian, simon',
author_email='mail@adrianwesth.dk',
maintainer='simon, adrian',
Expand Down