def __init__(self, obs_dim, act_dim, size, 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.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, 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.gamma, self.lam = gamma, lam
self.device = torch.device(
"cuda") if torch.cuda.is_available() else torch.device("cpu")
self.device = torch.device("cpu")
self.ptr, self.path_start_idx, self.max_size = 0, 0, size
def __init__(self,
obs_dim,
act_dim,
size,
gamma=0.99,
lam=0.95,
hierstep=3):
self.obs_buf = np.zeros(core.combined_shape(size, obs_dim),
dtype=np.float32)
self.init_obs_buf = np.zeros(core.combined_shape(size, obs_dim),
dtype=np.float32)
self.goal_buf = np.zeros(core.combined_shape(size, obs_dim),
dtype=np.float32)
self.count_buf = np.zeros(core.combined_shape(size, act_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.obshi_buf = np.zeros(core.combined_shape(size, obs_dim),
dtype=np.float32)
self.acthi_buf = np.zeros(core.combined_shape(size, obs_dim),
dtype=np.float32)
self.advhi_buf = np.zeros(size, dtype=np.float32)
self.rewhi_buf = np.zeros(size, dtype=np.float32)
self.rethi_buf = np.zeros(size, dtype=np.float32)
self.valhi_buf = np.zeros(size, dtype=np.float32)
self.logphi_buf = np.zeros(size, dtype=np.float32)
self.gamma, self.lam, self.hierstep = gamma, lam, hierstep
self.ptr, self.path_start_idx, self.max_size = 0, 0, size
self.ptrhi, self.path_start_idxhi = 0, 0
