Skip to content
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

Jump to bottom

Hotfix behavior descriptor #13

Merged
merged 5 commits into from
Jun 8, 2022
Merged

Hotfix behavior descriptor #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6051206
fix(links): update links in README and notebooks
felixchalumeau May 31, 2022
47eb535
Merge remote-tracking branch 'upstream/main' into main
felixchalumeau May 31, 2022
330743a
fix: udpate notebook to fix issue with bd evaluation
felixchalumeau Jun 2, 2022
696ff88
quick minor fix in the notebook
felixchalumeau Jun 2, 2022
a83b9b9
reduce episode length and iterations in pgame notebook
felixchalumeau Jun 2, 2022
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
6 changes: 4 additions & 2 deletions notebooks/mapelites_example.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@
"outputs": [],
"source": [
"# Init environment\n",
"env = environments.create(env_name)\n",
"env = environments.create(env_name, episode_length=episode_length)\n",
"\n",
"# Init a random key\n",
"random_key = jax.random.PRNGKey(seed)\n",
Expand Down Expand Up @@ -161,6 +161,8 @@
" \"\"\"\n",
"\n",
" actions = policy_network.apply(policy_params, env_state.obs)\n",
" \n",
" state_desc = env_state.info[\"state_descriptor\"]\n",
" next_state = env.step(env_state, actions)\n",
"\n",
" transition = QDTransition(\n",
Expand All @@ -170,7 +172,7 @@
" dones=next_state.done,\n",
" actions=actions,\n",
" truncations=next_state.info[\"truncation\"],\n",
" state_desc=env_state.info[\"state_descriptor\"],\n",
" state_desc=state_desc,\n",
" next_state_desc=next_state.info[\"state_descriptor\"],\n",
" )\n",
"\n",
Expand Down
6 changes: 4 additions & 2 deletions notebooks/pgame_example.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@
"outputs": [],
"source": [
"# Init environment\n",
"env = environments.create(env_name)\n",
"env = environments.create(env_name, episode_length=episode_length)\n",
"\n",
"# Init a random key\n",
"random_key = jax.random.PRNGKey(seed)\n",
Expand Down Expand Up @@ -169,6 +169,8 @@
" \"\"\"\n",
"\n",
" actions = policy_network.apply(policy_params, env_state.obs)\n",
" \n",
" state_desc = env_state.info[\"state_descriptor\"]\n",
" next_state = env.step(env_state, actions)\n",
"\n",
" transition = QDTransition(\n",
Expand All @@ -178,7 +180,7 @@
" dones=next_state.done,\n",
" actions=actions,\n",
" truncations=next_state.info[\"truncation\"],\n",
" state_desc=env_state.info[\"state_descriptor\"],\n",
" state_desc=state_desc,\n",
" next_state_desc=next_state.info[\"state_descriptor\"],\n",
" )\n",
"\n",
Expand Down
6 changes: 4 additions & 2 deletions tests/core_test/map_elites_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ def test_map_elites() -> None:
max_bd = 1.0

# Init environment
env = environments.create(env_name)
env = environments.create(env_name, episode_length=episode_length)

# Init a random key
random_key = jax.random.PRNGKey(seed)
Expand Down Expand Up @@ -65,6 +65,8 @@ def play_step_fn(
"""

actions = policy_network.apply(policy_params, env_state.obs)

state_desc = env_state.info["state_descriptor"]
next_state = env.step(env_state, actions)

transition = QDTransition(
Expand All @@ -74,7 +76,7 @@ def play_step_fn(
dones=next_state.done,
actions=actions,
truncations=next_state.info["truncation"],
state_desc=env_state.info["state_descriptor"],
state_desc=state_desc,
next_state_desc=next_state.info["state_descriptor"],
)

Expand Down
6 changes: 4 additions & 2 deletions tests/core_test/pgame_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ def test_pgame_elites() -> None:
num_pg_training_steps = 5

# Init environment
env = environments.create(env_name)
env = environments.create(env_name, episode_length=episode_length)

# Init a random key
random_key = jax.random.PRNGKey(seed)
Expand Down Expand Up @@ -77,6 +77,8 @@ def play_step_fn(
"""

actions = policy_network.apply(policy_params, env_state.obs)

state_desc = env_state.info["state_descriptor"]
next_state = env.step(env_state, actions)

transition = QDTransition(
Expand All @@ -86,7 +88,7 @@ def play_step_fn(
dones=next_state.done,
actions=actions,
truncations=next_state.info["truncation"],
state_desc=env_state.info["state_descriptor"],
state_desc=state_desc,
next_state_desc=next_state.info["state_descriptor"],
)

Expand Down