We lifted 8 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| instadeepai/poppy | pwc_unofficial | 5 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| get_acting_keys | Ran | instadeepai/poppy/poppy/utils/data.py code served (permissive licence) · get_code("996e62c4cd6ed060") |
| get_agent_contributions | Ran | instadeepai/poppy/poppy/utils/metrics.py code served (permissive licence) · get_code("68f8056fb0caa770") |
| get_optimizer | Ran | instadeepai/poppy/poppy/trainers/trainer.py code served (permissive licence) · get_code("6f3252b61d4427b7") |
| get_pop_performance_with_random_agents | Ran | instadeepai/poppy/poppy/utils/metrics.py code served (permissive licence) · get_code("fb96068e6f59c9ac") |
| get_start_positions | Ran | instadeepai/poppy/poppy/utils/data.py code served (permissive licence) · get_code("883057f04316e98e") |
| get_metrics | Not yet run | instadeepai/poppy/poppy/utils/metrics.py code served (permissive licence) · get_code("05089f65276ed271") |
| get_params | Not yet run | instadeepai/poppy/poppy/trainers/validation.py code served (permissive licence) · get_code("a5bda23e4f88eecf") |
| load_checkpoint | Not yet run | instadeepai/poppy/poppy/utils/checkpoint.py code served (permissive licence) · get_code("5720de557f409693") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge or pre-solved instances. However, it is unrealistic to expect an agent to solve these (often NP-)hard problems in a single shot at inference due to their inherent complexity. Thus, leading approaches often implement additional search strategies, from stochastic sampling and beam search to explicit fine-tuning. In this paper, we argue for the benefits of learning a population of complementary policies, which can be simultaneously rolled out at inference. To this end, we introduce Poppy, a simple training procedure for populations. Instead of relying on a predefined or hand-crafted notion of diversity, Poppy induces an unsupervised specialization targeted solely at maximizing the performance of the population. We show that Poppy produces a set of complementary policies, and obtains state-of-the-art RL results on four popular NP-hard problems: traveling salesman, capacitated vehicle routing, 0-1 knapsack, and job-shop scheduling.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.03475")
get_code_for_paper("2210.03475")
have("2210.03475")
Connect an agent — have() is free.