def __init__(self,
obs_dim,
act_dim,
size,
info_shapes,
gamma=0.99,
lam=0.95):
"""
Initialize properties:
Environment:
observations, actions, rewards, total expected rewards
Computed:
advantages, values, logps, infos,
Training:
gamma, lam
Store:
path trajectory, path start index, max size of store
Get sorted info keys
"""
self.obs_buf = np.zeros(core.combined_shape(size, obs_dim),
dtype=np.float32)
self.act_buf = np.zeros(core.combined_shape(size, act_dim),
dtype=np.float32)
self.adv_buf = np.zeros(size, dtype=np.float32)
self.rew_buf = np.zeros(size, dtype=np.float32)
self.ret_buf = np.zeros(size, dtype=np.float32)
self.val_buf = np.zeros(size, dtype=np.float32)
self.logp_buf = np.zeros(size, dtype=np.float32)
self.info_bufs = {
k: np.zeros([size] + list(v), dtype=np.float32)
for k, v in info_shapes.items()
}
self.sorted_info_keys = core.keys_as_sorted_list(self.info_bufs)
self.gamma, self.lam = gamma, lam
self.ptr, self.path_start_idx, self.max_size = 0, 0, size
def __init__(self,
obs_dim,
act_dim,
size,
info_shapes,
gamma=0.99,
lam=0.95):
self.obs_buf = np.zeros(core.combined_shape(size, obs_dim),
dtype=np.float32)
self.act_buf = np.zeros(core.combined_shape(size, act_dim),
dtype=np.float32)
self.adv_buf = np.zeros(size, dtype=np.float32)
self.rew_buf = np.zeros(size, dtype=np.float32)
self.ret_buf = np.zeros(size, dtype=np.float32)
self.val_buf = np.zeros(size, dtype=np.float32)
self.logp_buf = np.zeros(size, dtype=np.float32)
self.info_bufs = {
k: np.zeros([size] + list(v), dtype=np.float32)
for k, v in info_shapes.items()
}
self.sorted_info_keys = core.keys_as_sorted_list(self.info_bufs)
self.gamma, self.lam = gamma, lam
self.ptr, self.path_start_idx, self.max_size = 0, 0, size