An important ML training paradigm is Reinforcement Learning (RL). RL models rely on a reward value generated at the end of each training run/ epoch to update the parameters (weights) of the model. This is different from the other ML methods such as Supervised Learning where labelled data/ examples are given from which the models learns. It's is also different from the Unsupervised Learning approach where inherent features of the unlabeled data are explored used by the model through the learning phase to identify clusters, etc.
The keras-io examples has some RL implementations such as actor_critic, ppo, etc. All of them work solely with the TensorFlow (tf) backend. In keras_io_examples_rl these have been ported to the Torch/ PyTorch backend. The typical changes include:
- Torch Imports
- Use torch specific Optimizer - torch.optim.Adam
- deep_q_network_breakout_pytorch () requires grad_clipping, in torch done before optimizer.step()
- Gradient computations in torch
- Replace tf GradientTape with torch autograd
- Disable gradient globally torch.set_grad_enabled(False)
- Enable autograd within specific flows/ methods where needed
- Call loss.backward(), optimizer.step() for backpropagation
- Few torch specific tensor & function changes/ wrappers
The ported pytorch compatible files are:
- actor_critic_cartpole_pytorch.py
- ddpg_pendulum_pytorch.py
- deep_q_network_breakout_pytorch.py
- ppo_cartpole_pytorch.py
References
- http://www.derongliu.org/adp/adp-cdrom/Barto1983.pdf
- https://hal.inria.fr/hal-00840470/document
- https://link.springer.com/content/pdf/10.1007/BF00992698.pdf
- https://www.semanticscholar.org/paper/Human-level-control-through-deep-reinforcement-Mnih-Kavukcuoglu/340f48901f72278f6bf78a04ee5b01df208cc508
- Continuous control with deep reinforcement learning: https://arxiv.org/abs/1509.02971)
- Deep Deterministic Policy Gradient (DDPG)
- https://gymnasium.farama.org/
- Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto
No comments:
Post a Comment