Pfrl

Enhancements
- Fix TypeError in pad_sequence for torch>=1.9.0 (163)
- Make `Monitor` optional (167)
- Fix for issue (174, thanks jfrancis71!)
- Fixed save/load problem on dqn.py (184, thanks jmribeiro!)

Bug fixes
- [BUGFIX] use functools.partial instead of lambda (157, thanks zhouzypaul!)

Documentation
- Fixes a minor typo (161, thanks prabhatnagarajan!)

Testing
- Fix CI error due to gym's version (159)
- Specify the version of traitlets to fix CI error (169)
- Fix mypy error due to numbers.Number (171)
- Fix lint errors (185)
- Pin pyglet==1.5.27 in CI to avoid errors (187)

Enhancements
- Add parameter to generate_exp_id() (115)
- add episode length statistics to evaluator (121, thanks tkelestemur!)
- call evaluation_hooks in Evaluator (122)
- Remove six dependency in pre-trained models (148)

Bug fixes
- Fix an error related to collation and RNN (129, thanks tarokiritani!)
- fix IndexError due to empty stack (133, thanks lerrytang!)

Documentation
- Adds pretrained models column to README (119)
- Adds mypy to contributing md (125)
- Updates BibTeX to JMLR paper (134)
- Adds link to paper (135)
- Adds links to blog posts in the README (137)
- Fix NormalizeActionSpace's comment (142)

Testing
- Use latest black (116)
- Switch to mypy>=0.800 (127)

Enhancements
- Remove deprecated SumTree (110)

Bug fixes
- Install filelock (113)

Enhancements
- Add type hints to DQN and its dependencies (17)
- Pretrained models (33)
- Optuna integration & example script (2) (46)
- Save and load a module trained with DataParallel or DistributedDataParallel (55)
- Replace nn.functional.tanh with torch.tanh (64)
- Makes common write_header function (71)
- Eval stats collector (80)
- Set stats type (83)
- Add `step_hooks` and `optimizer_step_hooks` to actor-learner (86)
- Adds env_stats to record_tb_stats (98)

Bug fixes
- calculate scalar q_values to log average_q statistics in categorical dqn algorithms (32)
- Detach greedy_actions before calling cpu() (81)
- Fix the hang in `train_agent_async` with Tensorboard (89)

Examples
- Pretrained models (33)
- [Fix Examples] function call was duplicated (36, thanks gorogoroyasu!)
- Optuna integration & example script (2) (46)

Testing
- Enable auto assignment of PR reviewers (43)
- Enable auto review assignment for PRs from forks (62)
- Activate auto assign only when a PR is opened (66)
- Adopt isort to format import sentences (82)
- Fixes flake errors (104)