huangfu/InteractionImitation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add SHAIL

Browse Source
This commit is contained in:
ebuehrle
2022-02-17 23:49:06 +01:00
parent 9de6bfe9a3
commit 1624e1a349
11 changed files with 79 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/core/gail.py
View File

@@ -1,10 +1,10 @@
import torch
import torch.nn.functional as F
from dataclasses import dataclass
from core.reparam_module import ReparamPolicy
from core.sampling import rollout
from core.trpo import trpo_step
from core.ppo import ppo_step
from src.core.reparam_module import ReparamPolicy
from src.core.sampling import rollout
from src.core.trpo import trpo_step
from src.core.ppo import ppo_step
from tqdm import tqdm
class TerminalLogger:

4
src/core/ppo.py
View File

@@ -1,6 +1,6 @@
import torch
from core.sampling import rollout
from core.value_estimation import gae
from src.core.sampling import rollout
from src.core.value_estimation import gae
def ppo(env_fn, value, policy, epochs, rollout_episodes, rollout_steps, gamma, gae_lambda, clip_ratio, pi_opt, pi_iters, v_opt, v_iters, target_kl=None, max_grad_norm=None):

8
src/core/trpo.py
View File

@@ -1,8 +1,8 @@
import torch
from core.reparam_module import ReparamPolicy
from core.sampling import rollout
from core.value_estimation import gae
from core.optimization import conjugate_gradient, line_search
from src.core.reparam_module import ReparamPolicy
from src.core.sampling import rollout
from src.core.value_estimation import gae
from src.core.optimization import conjugate_gradient, line_search
def trpo(env_fn, value, policy, epochs, rollout_episodes, rollout_steps, gamma, gae_lambda, delta, backtrack_coeff, backtrack_iters, v_opt, v_iters, cg_iters=10, cg_damping=0.1):