PPO Agent playing Walker2DBulletEnv-v0

This is a trained model of a PPO agent playing Walker2DBulletEnv-v0 using the /sgoodfriend/rl-algo-impls repo.

All models trained at this commit can be found at https://api.wandb.ai/links/sgoodfriend/ysd5gj7p.

Training Results

This model was trained from 3 trainings of PPO agents using different initial seeds. These agents were trained by checking out 983cb75. The best and last models were kept from each training. This submission has loaded the best models from each training, reevaluates them, and selects the best model from these latest evaluations (mean - std).

algo	env	seed	reward_mean	reward_std	eval_episodes	best	wandb_url
ppo	Walker2DBulletEnv-v0	1	1943.44	6.02595	16	*	wandb
ppo	Walker2DBulletEnv-v0	2	1821.93	13.1212	16		wandb
ppo	Walker2DBulletEnv-v0	3	2109.58	509.27	16		wandb

Prerequisites: Weights & Biases (WandB)

Training and benchmarking assumes you have a Weights & Biases project to upload runs to. By default training goes to a rl-algo-impls project while benchmarks go to rl-algo-impls-benchmarks. During training and benchmarking runs, videos of the best models and the model weights are uploaded to WandB.

Before doing anything below, you'll need to create a wandb account and run wandb login.

Usage

/sgoodfriend/rl-algo-impls: https://github.com/sgoodfriend/rl-algo-impls

Note: While the model state dictionary and hyperaparameters are saved, the latest implementation could be sufficiently different to not be able to reproduce similar results. You might need to checkout the commit the agent was trained on: 983cb75.

# Downloads the model, sets hyperparameters, and runs agent for 3 episodes
python enjoy.py --wandb-run-path=sgoodfriend/rl-algo-impls-benchmarks/ldhyo09q

Setup hasn't been completely worked out yet, so you might be best served by using Google Colab starting from the colab_enjoy.ipynb notebook.

Training

If you want the highest chance to reproduce these results, you'll want to checkout the commit the agent was trained on: 983cb75. While training is deterministic, different hardware will give different results.

python train.py --algo ppo --env Walker2DBulletEnv-v0 --seed 1

Setup hasn't been completely worked out yet, so you might be best served by using Google Colab starting from the colab_train.ipynb notebook.

Benchmarking (with Lambda Labs instance)

This and other models from https://api.wandb.ai/links/sgoodfriend/ysd5gj7p were generated by running a script on a Lambda Labs instance. In a Lambda Labs instance terminal:

git clone [email protected]:sgoodfriend/rl-algo-impls.git
cd rl-algo-impls
bash ./lambda_labs/setup.sh
wandb login
bash ./lambda_labs/benchmark.sh [-a {"ppo a2c dqn vpg"}] [-e ENVS] [-j {6}] [-p {rl-algo-impls-benchmarks}] [-s {"1 2 3"}]

Alternative: Google Colab Pro+

As an alternative, colab_benchmark.ipynb, can be used. However, this requires a Google Colab Pro+ subscription and running across 4 separate instances because otherwise running all jobs will exceed the 24-hour limit.

Hyperparameters

This isn't exactly the format of hyperparams in hyperparams/ppo.yml, but instead the Wandb Run Config. However, it's very close and has some additional data:

additional_keys_to_log: []
algo: ppo
algo_hyperparams:
  batch_size: 128
  clip_range: 0.4
  clip_range_decay: linear
  ent_coef: 0
  gae_lambda: 0.9
  gamma: 0.99
  learning_rate: 3.0e-05
  max_grad_norm: 0.5
  n_epochs: 20
  n_steps: 512
  vf_coef: 0.5
device: auto
env: Walker2DBulletEnv-v0
env_hyperparams:
  n_envs: 16
  normalize: true
env_id: null
eval_hyperparams: {}
microrts_reward_decay_callback: false
n_timesteps: 2000000
policy_hyperparams:
  activation_fn: relu
  pi_hidden_sizes:
  - 256
  - 256
  v_hidden_sizes:
  - 256
  - 256
seed: 1
use_deterministic_algorithms: true
wandb_entity: null
wandb_group: null
wandb_project_name: rl-algo-impls-benchmarks
wandb_tags:
- benchmark_983cb75
- host_129-159-43-75
- branch_main
- v0.0.9

sgoodfriend
/

ppo-Walker2DBulletEnv-v0