Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 1 addition & 2 deletions pufferlib/config/mujoco.ini
Original file line number Diff line number Diff line change
Expand Up @@ -10,10 +10,10 @@ render_mode = rgb_array
[vec]
num_envs = 512
num_workers = 16
batch_size = auto

[train]
total_timesteps = 5_000_000
batch_size = auto
learning_rate = 3e-4
gamma = 0.99
gae_lambda = 0.95
Expand All @@ -24,6 +24,5 @@ vf_clip_coef = 0.2
max_grad_norm = 0.5
ent_coef = 0.0
checkpoint_interval = 200
batch_size = 32768
minibatch_size = 4096
bptt_horizon = 64
16 changes: 4 additions & 12 deletions pufferlib/environments/mujoco/environment.py
Original file line number Diff line number Diff line change
Expand Up @@ -11,21 +11,15 @@
import pufferlib.environments


def single_env_creator(env_name, capture_video, gamma,
def single_env_creator(env_name, gamma,
run_name=None, idx=None, obs_norm=True, pufferl=False, render_mode='rgb_array', buf=None, seed=0):
if capture_video and idx == 0:
assert run_name is not None, "run_name must be specified when capturing videos"
env = gymnasium.make(env_name, render_mode="rgb_array")
env = gymnasium.wrappers.RecordVideo(env, f"videos/{run_name}")
else:
env = gymnasium.make(env_name, render_mode=render_mode)

env = gymnasium.make(env_name, render_mode=render_mode)
env = pufferlib.ClipAction(env) # NOTE: this changed actions space
env = pufferlib.EpisodeStats(env)

if obs_norm:
env = gymnasium.wrappers.NormalizeObservation(env)
env = gymnasium.wrappers.TransformObservation(env, lambda obs: np.clip(obs, -10, 10), env.observation_space)
env = gymnasium.wrappers.TransformObservation(env, lambda obs: np.clip(obs, -10, 10))

env = gymnasium.wrappers.NormalizeReward(env, gamma=gamma)
env = gymnasium.wrappers.TransformReward(env, lambda reward: np.clip(reward, -10, 10))
Expand All @@ -36,11 +30,10 @@ def single_env_creator(env_name, capture_video, gamma,
return env


def cleanrl_env_creator(env_name, run_name, capture_video, gamma, idx):
def cleanrl_env_creator(env_name, run_name, gamma, idx):
kwargs = {
"env_name": env_name,
"run_name": run_name,
"capture_video": capture_video,
"gamma": gamma,
"idx": idx,
"pufferl": False,
Expand All @@ -52,7 +45,6 @@ def cleanrl_env_creator(env_name, run_name, capture_video, gamma, idx):
def env_creator(env_name="HalfCheetah-v4", gamma=0.99):
default_kwargs = {
"env_name": env_name,
"capture_video": False,
"gamma": gamma,
"pufferl": True,
}
Expand Down
3 changes: 1 addition & 2 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -149,8 +149,7 @@ minihack = [
]

mujoco = [
'gymnasium[mujoco]==1.0.0',
'moviepy',
'gymnasium[mujoco]==0.29.1',
]

nethack = [
Expand Down
Loading