We lifted 5 functions out of this paper's own repositories and ran 4 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 |
|---|---|---|
| moreanp/csro | canonical | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| create_stats_ordered_dict | Ran | moreanp/csro/rlkit/core/eval_util.py pointer only (licence: NONE) · get_code("f395bfda2e4813d7") |
| deep_update_dict | Ran | moreanp/csro/launch_experiment.py pointer only (licence: NONE) · get_code("e937b70b07bfc9d1") |
| get_average_returns | Ran | moreanp/csro/rlkit/core/eval_util.py pointer only (licence: NONE) · get_code("a5d10a0b704c8db7") |
| get_generic_path_information | Ran | moreanp/csro/rlkit/core/eval_util.py pointer only (licence: NONE) · get_code("c809703793017cd2") |
| register_license | Not yet run | moreanp/csro/rand_param_envs/mujoco_py/mjcore.py pointer only (licence: NONE) · get_code("5480531658d82335") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets. The key insight of CSRO is to minimize the influence of policy in context during both the meta-training and meta-test phases. During meta-training, we design a max-min mutual information representation learning mechanism to diminish the impact of the behavior policy on task representation. In the meta-test phase, we introduce the non-prior context collection strategy to reduce the effect of the exploration policy. Experimental results demonstrate that CSRO significantly reduces the context shift and improves the generalization ability, surpassing previous methods across various challenging domains.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.03695")
get_code_for_paper("2311.03695")
have("2311.03695")
Connect an agent — have() is free.