We lifted 11 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| zhaohengyin/irgail_example | canonical | 2 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| build_mlp | Ran | zhaohengyin/irgail_example/imitation_learning/network/utils.py code served (permissive licence) · get_code("c511268a73d82fc6") |
| calculate_gae | Ran | zhaohengyin/irgail_example/imitation_learning/algo/ppo.py code served (permissive licence) · get_code("b5a22b5e0dce3796") |
| build_mlp | Not yet run | zhaohengyin/irgail_example/utils.py code served (permissive licence) · get_code("07de2bbbb9d4b7a3") |
| build_mlp_gaussian | Not yet run | zhaohengyin/irgail_example/imitation_learning/network/utils.py code served (permissive licence) · get_code("86615daab498a894") |
| cross_entropy_loss | Not yet run | zhaohengyin/irgail_example/imitation_learning/network/utils.py code served (permissive licence) · get_code("b4cee438c3091f1c") |
| dict_concat | Not yet run | zhaohengyin/irgail_example/utils.py code served (permissive licence) · get_code("25af8d867eb0b1fc") |
| dict_config_concat | Not yet run | zhaohengyin/irgail_example/utils.py code served (permissive licence) · get_code("d4366d9ad0077796") |
| make_env | Not yet run | zhaohengyin/irgail_example/imitation_learning/env.py code served (permissive licence) · get_code("e10629e58933d321") |
| move_to_gpu | Not yet run | zhaohengyin/irgail_example/torch_utils.py code served (permissive licence) · get_code("9adc9bf5872c56b6") |
| numpy_to_tensor | Not yet run | zhaohengyin/irgail_example/torch_utils.py code served (permissive licence) · get_code("d08f0bcf823029e2") |
| scalar_to_tensor | Not yet run | zhaohengyin/irgail_example/torch_utils.py code served (permissive licence) · get_code("fa9d343b9aae2ea2") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Animals are able to imitate each others' behavior, despite their difference in biomechanics. In contrast, imitating the other similar robots is a much more challenging task in robotics. This problem is called cross domain imitation learning~(CDIL). In this paper, we consider CDIL on a class of similar robots. We tackle this problem by introducing an imitation learning algorithm based on invariant representation. We propose to learn invariant state and action representations, which aligns the behavior of multiple robots so that CDIL becomes possible. Compared with previous invariant representation learning methods for similar purpose, our method does not require human-labeled pairwise data for training. Instead, we use cycle-consistency and domain confusion to align the representation and increase its robustness. We test the algorithm on multiple robots in simulator and show that unseen new robot instances can be trained with existing expert demonstrations successfully. Qualitative results also demonstrate that the proposed method is able to learn similar representations for different robots with similar behaviors, which is essential for successful CDIL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.05940")
get_code_for_paper("2109.05940")
have("2109.05940")
Connect an agent — have() is free.