v0.2.0

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)