hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fixed env seeding in test_sac_with_il.py (#1081)

Browse Source
This commit is contained in:
maxhuettenrauch 2024-03-28 12:52:35 +01:00 committed by GitHub
parent 61bf9adaff
commit edae9e4403
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
test/continuous/test_sac_with_il.py
View File

@ -78,6 +78,8 @@ def test_sac_with_il(args: argparse.Namespace = get_args()) -> None:
# seed
np.random.seed(args.seed)
torch.manual_seed(args.seed)
train_envs.seed(args.seed)
test_envs.seed(args.seed + args.training_num)
# model
net = Net(args.state_shape, hidden_sizes=args.hidden_sizes, device=args.device)
actor = ActorProb(net, args.action_shape, device=args.device, unbounded=True).to(args.device)
@ -181,10 +183,12 @@ def test_sac_with_il(args: argparse.Namespace = get_args()) -> None:
action_scaling=True,
action_bound_method="clip",
)
il_test_env = gym.make(args.task)
il_test_env.reset(seed=args.seed + args.training_num + args.test_num)
il_test_collector = Collector(
il_policy,
# envpool.make_gymnasium(args.task, num_envs=args.test_num, seed=args.seed),
gym.make(args.task),
il_test_env,
)
train_collector.reset()
result = OffpolicyTrainer(