* `learn.py` is now main script for training brains.
* Simultaneous multi-brain training is now possible.
* `ghost-trainer` allows for proper training in adversarial scenarios.
* `imitation-trainer` provides a basic implementation of real-time behavioral cloning.
* All trainer hyperparameters now exist in `.yaml` files.
* `PPO.ipynb` removed.
* LSTM model added.
* More dynamic buffer class to handle greater variety of scenarios.
* Add support for stacking past n states to allow network to learn temporal dependencies.
* Add Banana Collector environment for demonstrating partially observable multi-agent environments.
* Add 3DBall Hard which lacks velocity information in state representation. Used as test for LSTM and state-stacking features.
* Rework Tennis environment to be continuous control and trainable in 100k steps.
* Add ability to seed learning (numpy, tensorflow, and Unity) with `--seed` flag.
* Add `maxStepReached` flag to Agents and Academy.
* Change way value bootstrapping works in PPO to take advantage of timeouts.
* Default size of GridWorld changed to 5x5 in order to validate bootstrapping changes.
* On Demand Decision : Use RequestDecision and RequestAction
* New Agent Inspector : Use it to set On Demand Decision
* New BrainParameters interface
* LSTM memory size is now set in python
* New C# API
* Semantic Changes
* Replaced RunMDP
* New Bouncer Environment to test On Demand Dscision
* Enable buffer padding to be set other than 0
Allows buffer padding in AgentBufferField to be set to a custom value. In particular, 0-padding for `action_masks` causes a divide-by-zero error, and should be padded with 1’s instead.
This is done as a parameter passed to the `append` method, so that the pad value can be set right after the instantiation of an AgentBufferField.
- Move common functions to trainer.py, model.pyfromppo/trainer.py, ppo/policy.pyandppo/model.py'
- Introduce RLTrainer class and move most of add_experiences and some common reward
signal code there. PPO and SAC will inherit from this, not so much BC Trainer.
- Add methods to Buffer to enable sampling, truncating, and save/loading.
- Add scoping to create encoders in model.py
We have been ignoring unused imports and star imports via flake8. These are
both bad practice and grow over time without automated checking. This
commit attempts to fix all existing import errors and add back the corresponding
flake8 checks.
This is the first in a series of PRs that intend to move the agent processing logic (add_experiences and process_experiences) out of the trainer and into a separate class. The plan is to do so in steps:
- Split the processing buffers (keeping track of agent trajectories and assembling trajectories) and update buffer (complete trajectories to be used for training) within the Trainer (this PR)
- Move the processing buffer and add/process experiences into a separate, outside class
- Change the data type of the update buffer to be a Trajectory
- Place and read Trajectories from queues, add subscription mechanism for both AgentProcessor and Trainers
* Added Reward Providers for Torch
* Use NetworkBody to encode state in the reward providers
* Integrating the reward prodiders with ppo and torch
* work in progress, integration with PPO. Not training properly Pyramids at the moment
* Integration in PPO
* Removing duplicate file
* Gail and Curiosity working
* addressing comments
* Enfore float32 for tests
* enfore np.float32 in buffer
Arthur Juliani
GitHub
Deric Pang
eshvk
Chris Elion
Ervin Teng
Christopher Goy
Andrew Cohen