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

29 lines
1002 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
fix venv seed, add TOC in docs, and split buffer.py into several files (#303) Things changed in this PR: - various docs update, add TOC - split buffer into several files - fix venv action_space randomness
2021-03-02 12:28:28 +08:00
from tianshou.data.buffer.base import ReplayBuffer
from tianshou.data.buffer.prio import PrioritizedReplayBuffer
from tianshou.data.buffer.manager import ReplayBufferManager
from tianshou.data.buffer.manager import PrioritizedReplayBufferManager
from tianshou.data.buffer.vecbuf import VectorReplayBuffer
from tianshou.data.buffer.vecbuf import PrioritizedVectorReplayBuffer
from tianshou.data.buffer.cached import CachedReplayBuffer
Step collector implementation (#280) This is the third PR of 6 commits mentioned in #274, which features refactor of Collector to fix #245. You can check #274 for more detail. Things changed in this PR: 1. refactor collector to be more cleaner, split AsyncCollector to support asyncvenv; 2. change buffer.add api to add(batch, bffer_ids); add several types of buffer (VectorReplayBuffer, PrioritizedVectorReplayBuffer, etc.) 3. add policy.exploration_noise(act, batch) -> act 4. small change in BasePolicy.compute_*_returns 5. move reward_metric from collector to trainer 6. fix np.asanyarray issue (different version's numpy will result in different output) 7. flake8 maxlength=88 8. polish docs and fix test Co-authored-by: n+e <trinkle23897@gmail.com>
2021-02-19 10:33:49 +08:00
from tianshou.data.collector import Collector, AsyncCollector
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",
"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",
Step collector implementation (#280) This is the third PR of 6 commits mentioned in #274, which features refactor of Collector to fix #245. You can check #274 for more detail. Things changed in this PR: 1. refactor collector to be more cleaner, split AsyncCollector to support asyncvenv; 2. change buffer.add api to add(batch, bffer_ids); add several types of buffer (VectorReplayBuffer, PrioritizedVectorReplayBuffer, etc.) 3. add policy.exploration_noise(act, batch) -> act 4. small change in BasePolicy.compute_*_returns 5. move reward_metric from collector to trainer 6. fix np.asanyarray issue (different version's numpy will result in different output) 7. flake8 maxlength=88 8. polish docs and fix test Co-authored-by: n+e <trinkle23897@gmail.com>
2021-02-19 10:33:49 +08:00
"PrioritizedReplayBufferManager",
"VectorReplayBuffer",
"PrioritizedVectorReplayBuffer",
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
"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",
Step collector implementation (#280) This is the third PR of 6 commits mentioned in #274, which features refactor of Collector to fix #245. You can check #274 for more detail. Things changed in this PR: 1. refactor collector to be more cleaner, split AsyncCollector to support asyncvenv; 2. change buffer.add api to add(batch, bffer_ids); add several types of buffer (VectorReplayBuffer, PrioritizedVectorReplayBuffer, etc.) 3. add policy.exploration_noise(act, batch) -> act 4. small change in BasePolicy.compute_*_returns 5. move reward_metric from collector to trainer 6. fix np.asanyarray issue (different version's numpy will result in different output) 7. flake8 maxlength=88 8. polish docs and fix test Co-authored-by: n+e <trinkle23897@gmail.com>
2021-02-19 10:33:49 +08:00
"AsyncCollector",
maybe finished collector?
2020-03-13 17:49:22 +08:00
]
Reference in New Issue Copy Permalink