Skip to content

Mighty rollout buffer

mighty.mighty_replay.mighty_rollout_buffer #

Mighty rollout buffer.

MightyRolloutBuffer #

MightyRolloutBuffer(
    buffer_size: int,
    obs_shape,
    act_dim,
    device: str = "auto",
    gae_lambda: float = 1,
    gamma: float = 0.99,
    n_envs: int = 1,
)

Bases: MightyBuffer

Rollout buffer used in on-policy algorithms like A2C/PPO.

Source code in mighty/mighty_replay/mighty_rollout_buffer.py 
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
def __init__(
    self,
    buffer_size: int,
    obs_shape,
    act_dim,
    device: str = "auto",
    gae_lambda: float = 1,
    gamma: float = 0.99,
    n_envs: int = 1,
):
    self.buffer_size = buffer_size
    self.obs_shape = obs_shape
    self.act_dim = act_dim
    self.device = device
    self.gae_lambda = gae_lambda
    self.gamma = gamma
    self.n_envs = n_envs
    self.reset()