@ -118,7 +118,7 @@ def ppo(args):
]
pprint.pprint({k: v for k, v in best_result.metrics.items() if k in metrics_to_print})
algo = Algorithm.from_checkpoint(best_result.checkpoint)
# algo = Algorithm.from_checkpoint(best_result.checkpoint)
# eval_log_dir = F"{logdir}-eval"
@ -42,7 +42,7 @@ def create_log_dir(args):
return F"{args.log_dir}sh:{args.shielding}-env:{args.env}"
def test_name(args):
return F"{args.expname}/sh:{args.shielding}-env:{args.env}"
return F"{args.expname}-sh:{args.shielding}-env:{args.env}"
def get_action_index_mapping(actions):
for action_str in actions: