dqn-Acrobot-v1 / README.md
sgoodfriend's picture
DQN playing Acrobot-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/983cb75e43e51cf4ef57f177194ab9a4a1a8808b
48f24b9
metadata
library_name: rl-algo-impls
tags:
  - Acrobot-v1
  - dqn
  - deep-reinforcement-learning
  - reinforcement-learning
model-index:
  - name: dqn
    results:
      - metrics:
          - type: mean_reward
            value: '-76.8 +/- 11.24'
            name: mean_reward
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: Acrobot-v1
          type: Acrobot-v1

DQN Agent playing Acrobot-v1

This is a trained model of a DQN agent playing Acrobot-v1 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 DQN 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
dqn Acrobot-v1 1 -76.8 11.241 10 * wandb
dqn Acrobot-v1 2 -125.7 127.202 10 wandb
dqn Acrobot-v1 3 -86.6 14.4859 10 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/m9lc7jvz

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 dqn --env Acrobot-v1 --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/dqn.yml, but instead the Wandb Run Config. However, it's very close and has some additional data:

additional_keys_to_log: []
algo: dqn
algo_hyperparams:
  batch_size: 128
  buffer_size: 50000
  exploration_final_eps: 0.1
  exploration_fraction: 0.12
  gamma: 0.99
  gradient_steps: -1
  learning_rate: 0.00063
  learning_starts: 0
  target_update_interval: 250
  train_freq: 4
device: auto
env: Acrobot-v1
env_hyperparams:
  rolling_length: 50
env_id: null
eval_hyperparams: {}
microrts_reward_decay_callback: false
n_timesteps: 100000
policy_hyperparams:
  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