Haonan Yu, Wei Xu, Haichao Zhang
We lifted 6 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 |
|---|---|---|
| haichao-zhang/pex | canonical | 4 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| epsilon_greedy_sample | Ran | haichao-zhang/pex/pex/algorithms/pex.py pointer only (licence: NONE) · get_code("b50e53f6458a72c5") |
| expectile_loss | Ran | haichao-zhang/pex/pex/algorithms/pex.py pointer only (licence: NONE) · get_code("d62277986ed1bdb1") |
| extract_sub_dict | Ran | haichao-zhang/pex/pex/algorithms/pex.py pointer only (licence: NONE) · get_code("e46e952e360c047d") |
| get_mode | Ran | haichao-zhang/pex/pex/algorithms/pex.py pointer only (licence: NONE) · get_code("9a72b33265a2a6d9") |
| IQL | Not yet run | haichao-zhang/pex/pex/algorithms/pex.py pointer only (licence: NONE) · get_code("2fb51ea95768885e") |
| PEX | Not yet run | haichao-zhang/pex/pex/algorithms/pex.py pointer only (licence: NONE) · get_code("89e77b8d462fb74e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Pre-training with offline data and online fine-tuning using reinforcement learning is a promising strategy for learning control policies by leveraging the best of both worlds in terms of sample efficiency and performance. One natural approach is to initialize the policy for online learning with the one trained offline. In this work, we introduce a policy expansion scheme for this task. After learning the offline policy, we use it as one candidate policy in a policy set. We then expand the policy set with another policy which will be responsible for further learning. The two policies will be composed in an adaptive manner for interacting with the environment. With this approach, the policy previously learned offline is fully retained during online learning, thus mitigating the potential issues such as destroying the useful behaviors of the offline policy in the initial stage of online learning while allowing the offline policy participate in the exploration naturally in an adaptive manner. Moreover, new useful behaviors can potentially be captured by the newly added policy through learning. Experiments are conducted on a number of tasks and the results demonstrate the effectiveness of the proposed approach. Code is available: https://github.com/Haichao-Zhang/PEX.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.00935")
get_code_for_paper("2302.00935")
have("2302.00935")
Connect an agent — have() is free.