hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Tianshou/tianshou/data/__init__.py

21 lines
589 B
Python
Raw Normal View History

env and data
2020-03-11 09:09:56 +08:00
from tianshou.data.batch import Batch
code format and update function signatures (#213) Cherry-pick from #200 - update the function signature - format code-style - move _compile into separate functions - fix a bug in to_torch and to_numpy (Batch) - remove None in action_range In short, the code-format only contains function-signature style and `'` -> `"`. (pick up from [black](https://github.com/psf/black))
2020-09-12 15:39:01 +08:00
from tianshou.data.utils.converter import to_numpy, to_torch, to_torch_as
Improve PER (#159) - use segment tree to rewrite the previous PrioReplayBuffer code, add the test - enable all Q-learning algorithms to use PER
2020-08-06 10:26:24 +08:00
from tianshou.data.utils.segtree import SegmentTree
Add CachedReplayBuffer and ReplayBufferManager (#278) This is the second commit of 6 commits mentioned in #274, which features minor refactor of ReplayBuffer and adding two new ReplayBuffer classes called CachedReplayBuffer and ReplayBufferManager. You can check #274 for more detail. 1. Add ReplayBufferManager (handle a list of buffers) and CachedReplayBuffer; 2. Make sure the reserved keys cannot be edited by methods like `buffer.done = xxx`; 3. Add `set_batch` method for manually choosing the batch the ReplayBuffer wants to handle; 4. Add `sample_index` method, same as `sample` but only return index instead of both index and batch data; 5. Add `prev` (one-step previous transition index), `next` (one-step next transition index) and `unfinished_index` (the last modified index whose done==False); 6. Separate `alloc_fn` method for allocating new memory for `self._meta` when a new `(key, value)` pair comes in; 7. Move buffer's documentation to `docs/tutorials/concepts.rst`. Co-authored-by: n+e <trinkle23897@gmail.com>
2021-01-29 12:23:18 +08:00
from tianshou.data.buffer import ReplayBuffer, ListReplayBuffer, \
PrioritizedReplayBuffer, ReplayBufferManager, CachedReplayBuffer
half of collector
2020-03-12 22:20:33 +08:00
from tianshou.data.collector import Collector
env and data
2020-03-11 09:09:56 +08:00
maybe finished collector?
2020-03-13 17:49:22 +08:00
__all__ = [
code format and update function signatures (#213) Cherry-pick from #200 - update the function signature - format code-style - move _compile into separate functions - fix a bug in to_torch and to_numpy (Batch) - remove None in action_range In short, the code-format only contains function-signature style and `'` -> `"`. (pick up from [black](https://github.com/psf/black))
2020-09-12 15:39:01 +08:00
"Batch",
"to_numpy",
"to_torch",
"to_torch_as",
"SegmentTree",
"ReplayBuffer",
"ListReplayBuffer",
"PrioritizedReplayBuffer",
Add CachedReplayBuffer and ReplayBufferManager (#278) This is the second commit of 6 commits mentioned in #274, which features minor refactor of ReplayBuffer and adding two new ReplayBuffer classes called CachedReplayBuffer and ReplayBufferManager. You can check #274 for more detail. 1. Add ReplayBufferManager (handle a list of buffers) and CachedReplayBuffer; 2. Make sure the reserved keys cannot be edited by methods like `buffer.done = xxx`; 3. Add `set_batch` method for manually choosing the batch the ReplayBuffer wants to handle; 4. Add `sample_index` method, same as `sample` but only return index instead of both index and batch data; 5. Add `prev` (one-step previous transition index), `next` (one-step next transition index) and `unfinished_index` (the last modified index whose done==False); 6. Separate `alloc_fn` method for allocating new memory for `self._meta` when a new `(key, value)` pair comes in; 7. Move buffer's documentation to `docs/tutorials/concepts.rst`. Co-authored-by: n+e <trinkle23897@gmail.com>
2021-01-29 12:23:18 +08:00
"ReplayBufferManager",
"CachedReplayBuffer",
code format and update function signatures (#213) Cherry-pick from #200 - update the function signature - format code-style - move _compile into separate functions - fix a bug in to_torch and to_numpy (Batch) - remove None in action_range In short, the code-format only contains function-signature style and `'` -> `"`. (pick up from [black](https://github.com/psf/black))
2020-09-12 15:39:01 +08:00
"Collector",
maybe finished collector?
2020-03-13 17:49:22 +08:00
]
Reference in New Issue Copy Permalink